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. 104191
    Prev
    Next
    INDEX
    Explanations

    actions

    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
    _mirror
    -0.08
     stripes
    -0.07
    çi
    -0.07
     Stanford
    -0.07
    RON
    -0.07
    CLE
    -0.07
    _Al
    -0.06
    iPhone
    -0.06
     ost
    -0.06
    _dt
    -0.06
    POSITIVE LOGITS
     gaping
    0.06
    @Inject
    0.06
     Serious
    0.06
     민주
    0.06
    >true
    0.06
     Install
    0.06
    .Win
    0.06
    bservable
    0.06
     ऐस
    0.06
    (select
    0.06
    Activations Density 0.188%

    No Known Activations