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. 27-RESID-POST-AA
    6. 102064
    Prev
    Next
    INDEX
    Explanations

    crop

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    	handler
    -0.07
    ledo
    -0.07
     Princess
    -0.07
     advisors
    -0.06
     Malik
    -0.06
     Trustees
    -0.06
     Handler
    -0.06
    guide
    -0.06
     advisers
    -0.06
    <N
    -0.06
    POSITIVE LOGITS
     crop
    0.09
     crops
    0.09
     Crop
    0.08
    CHE
    0.07
    _SCOPE
    0.07
    ови
    0.07
     chore
    0.07
     compét
    0.07
    (EXPR
    0.07
    rena
    0.06
    Activations Density 0.004%

    No Known Activations