Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 94454
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jacob
    -0.07
     mening
    -0.07
    acob
    -0.07
     morning
    -0.07
    Emily
    -0.07
    .Sum
    -0.06
    صات
    -0.06
     Pam
    -0.06
     riders
    -0.06
    Answer
    -0.06
    POSITIVE LOGITS
     “
    0.09
     «
    0.08
     "
    0.07
     ‘
    0.07
    sez
    0.07
    averse
    0.07
     "_
    0.07
     Cas
    0.07
    -value
    0.06
     Std
    0.06
    Activations Density 0.129%

    No Known Activations