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. 109215
    Prev
    Next
    INDEX
    Explanations

    out

    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
     soud
    -0.07
     rout
    -0.07
    Ind
    -0.07
    Validators
    -0.07
    _Up
    -0.07
    _where
    -0.07
    aced
    -0.07
    Grad
    -0.06
    Measured
    -0.06
     impress
    -0.06
    POSITIVE LOGITS
    ighter
    0.07
     McG
    0.06
     Kb
    0.06
    ρηση
    0.06
     principio
    0.06
     common
    0.06
    >\<^
    0.06
     yn
    0.06
    민주
    0.06
    Obama
    0.06
    Activations Density 0.188%

    No Known Activations