© 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 (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 57237
    Prev
    Next
    INDEX
    Explanations

    //

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Foley
    -0.06
    وير
    -0.06
    ��
    -0.06
     Bride
    -0.06
    وک
    -0.06
     piping
    -0.06
     roll
    -0.06
    كر
    -0.06
     circus
    -0.06
    bus
    -0.06
    POSITIVE LOGITS
     dispar
    0.07
    áf
    0.06
     prox
    0.06
     nuanced
    0.06
     FT
    0.06
     slack
    0.06
    _$
    0.06
     dissertation
    0.06
     disparate
    0.06
    (Py
    0.06
    Activations Density 0.010%

    No Known Activations