© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 29980
    Prev
    Next
    INDEX
    Explanations

    Video game guide/tips

    np_max-act · gemini-2.0-flash

    The neuron flags first-person or self-referential expressions (e.g. “I,” “my experience,” “wouldn’t,” “don’t”).

    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
     BET
    -0.06
    �
    -0.06
    须
    -0.06
    many
    -0.06
     rych
    -0.06
     robert
    -0.06
    Doc
    -0.06
    _FAST
    -0.06
    ��
    -0.06
    렵
    -0.06
    POSITIVE LOGITS
    ,p
    0.08
    .TextChanged
    0.07
     arbitrarily
    0.07
     hidden
    0.07
    结
    0.07
    из
    0.06
     eventdata
    0.06
     Alla
    0.06
     internacional
    0.06
    encer
    0.06
    Activations Density 0.023%

    No Known Activations