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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 15-RESID-POST-AA
    6. 120472
    Prev
    Next
    INDEX
    Explanations

    Word fragments

    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
    Handling
    -0.07
    -R
    -0.07
    _M
    -0.07
     Fro
    -0.06
    )=>{↵
    -0.06
    スの
    -0.06
    _projection
    -0.06
    .ref
    -0.06
     drawbacks
    -0.06
    Object
    -0.06
    POSITIVE LOGITS
     Juda
    0.07
     jorn
    0.07
     Nam
    0.07
    尼
    0.06
     Zhu
    0.06
    著
    0.06
     AsyncStorage
    0.06
    pherd
    0.06
    जर
    0.06
    нач
    0.06
    Activations Density 0.074%

    No Known Activations