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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 128383
    Prev
    Next
    INDEX
    Explanations

    describing features

    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
     Zukunft
    -0.08
     decir
    -0.07
     subj
    -0.06
    _DEST
    -0.06
    .Members
    -0.06
     thief
    -0.06
    [args
    -0.06
    lations
    -0.06
    geber
    -0.06
                                                                                       
    -0.06
    POSITIVE LOGITS
     loading
    0.07
    ewood
    0.06
    _prior
    0.06
    Often
    0.06
    azel
    0.06
     fictional
    0.06
    (ib
    0.06
     Pascal
    0.06
    -ab
    0.06
     Ricky
    0.06
    Activations Density 0.218%

    No Known Activations