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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11-RESID-POST-AA
    6. 104150
    Prev
    Next
    INDEX
    Explanations

    technical descriptions

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _addr
    -0.06
    أم
    -0.06
    _are
    -0.06
    _index
    -0.06
    CID
    -0.06
     autopsy
    -0.06
    _rd
    -0.06
    -view
    -0.06
     dead
    -0.06
     realizes
    -0.06
    POSITIVE LOGITS
     bestimm
    0.08
     objekt
    0.08
     Nearby
    0.07
    .public
    0.07
    */↵↵
    0.07
    โลย
    0.07
     ApplicationDbContext
    0.07
     fotograf
    0.07
     trú
    0.07
     Puppet
    0.07
    Activations Density 0.062%

    No Known Activations