© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 91487
    Prev
    Next
    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on numeric parameter values—especially floating-point numbers—found in the serialized settings.

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

    technical specifications related to texture maps in file formats.

    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
    โรง
    -0.07
     сон
    -0.07
     automate
    -0.07
     Signature
    -0.07
    reten
    -0.07
    जन
    -0.07
    тах
    -0.06
     берег
    -0.06
     cerr
    -0.06
     mê
    -0.06
    POSITIVE LOGITS
    [self
    0.07
    939
    0.06
     {};↵
    0.06
     railing
    0.06
     denounced
    0.05
    _months
    0.05
    Hyper
    0.05
    :new
    0.05
     Zy
    0.05
    %'
    0.05
    Activations Density 0.008%

    No Known Activations