© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 69370
    Prev
    Next
    INDEX
    Explanations

    Soap

    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
     Girls
    -0.07
     CUR
    -0.07
     freight
    -0.07
     организм
    -0.07
     Funding
    -0.06
    iesz
    -0.06
    ーレ
    -0.06
     LGBTQ
    -0.06
     crises
    -0.06
    ์ร
    -0.06
    POSITIVE LOGITS
     soap
    0.11
     Soap
    0.11
    Soap
    0.09
     SOAP
    0.08
    soap
    0.08
    ezpe
    0.07
    woord
    0.07
    _pp
    0.06
    “This
    0.06
     olup
    0.06
    Activations Density 0.004%

    No Known Activations