© 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. 15-RESID-POST-AA
    6. 39697
    Prev
    Next
    INDEX
    Explanations

    special

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lin
    -0.07
     Nguyen
    -0.07
     calf
    -0.07
     Otto
    -0.07
    auge
    -0.06
    Enterprise
    -0.06
     Quinn
    -0.06
     Burke
    -0.06
    652
    -0.06
     domů
    -0.06
    POSITIVE LOGITS
     special
    0.11
     Special
    0.10
     Wel
    0.08
    IAL
    0.07
    AL
    0.07
     deals
    0.07
    Special
    0.07
    {s
    0.07
     �
    0.07
     specials
    0.07
    Activations Density 0.016%

    No Known Activations