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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 30209
    Prev
    Next
    INDEX
    Explanations

    similarity

    np_max-act · gemini-2.0-flash

    The neuron fires on comparative expressions indicating likeness or resemblance (e.g. “similar,” “resembles,” “closely similar to”).

    oai_token-act-pair · o4-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
    nos
    -0.07
     objeto
    -0.06
     nack
    -0.06
     PureComponent
    -0.06
    ylko
    -0.06
    ्यम
    -0.06
     kos
    -0.06
     hardwood
    -0.06
    メージ
    -0.06
     infusion
    -0.06
    POSITIVE LOGITS
     ],↵
    0.08
    _Native
    0.08
    MG
    0.07
    observations
    0.07
     )"
    0.06
    ]>=
    0.06
    现代
    0.06
    欠
    0.06
     ),↵↵
    0.06
     deton
    0.06
    Activations Density 0.031%

    No Known Activations