© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 129992
    Prev
    Next
    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on copular or linking‐verb phrases in definitional or biographical statements (e.g. “He is,” “is known,” “is considered,” “was remembered,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    references to historical figures and their achievements.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    });
↵
↵
    -0.07
     stubborn
    -0.06
     diameter
    -0.06
    883
    -0.06
     θ
    -0.06
     supports
    -0.06
    };
↵
↵
↵
    -0.06
     }}
↵
    -0.06
    Θ
    -0.06
    -regexp
    -0.06
    POSITIVE LOGITS
    .Country
    0.07
     сбор
    0.06
     pageTitle
    0.06
    rese
    0.06
     nhau
    0.06
    aternity
    0.06
    _variance
    0.06
    ağ
    0.06
    iyle
    0.06
     anticipate
    0.06
    Activations Density 0.028%

    No Known Activations