© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 77299
    Prev
    Next
    INDEX
    Explanations

    :

    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
     kurum
    -0.07
     문화
    -0.07
     CFR
    -0.06
                                                          
    -0.06
     options
    -0.06
    ział
    -0.06
     uch
    -0.06
    illow
    -0.06
     κό
    -0.06
    forum
    -0.06
    POSITIVE LOGITS
    acades
    0.06
     {
    ↵
    ↵
    ↵
    0.06
    :'.$
    0.06
    ジオ
    0.06
    agy
    0.06
    pellier
    0.06
    .TEST
    0.06
     Vacc
    0.06
    Compilation
    0.06
    Backdrop
    0.06
    Activations Density 0.007%

    No Known Activations