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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7-RESID-POST-AA
    6. 39395
    Prev
    Next
    INDEX
    Explanations

    the

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    召
    -0.08
    цез
    -0.07
    黨
    -0.06
    alus
    -0.06
    _cl
    -0.06
     letters
    -0.06
    71
    -0.06
    /c
    -0.06
    tip
    -0.06
     edge
    -0.06
    POSITIVE LOGITS
    αιν
    0.07
    μα
    0.06
    _interfaces
    0.06
    _empresa
    0.06
     Zero
    0.06
     января
    0.06
     Tüm
    0.06
     primeira
    0.06
     Dortmund
    0.06
    _AHB
    0.05
    Activations Density 0.046%

    No Known Activations