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. 11-RESID-POST-AA
    6. 53220
    Prev
    Next
    INDEX
    Explanations

    ATION

    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
    ่อส
    -0.07
    醴醴
    -0.06
     đào
    -0.06
    jack
    -0.06
     esc
    -0.06
     Bridge
    -0.06
     kitty
    -0.06
    atten
    -0.06
    ahun
    -0.06
    자료
    -0.06
    POSITIVE LOGITS
     전국
    0.07
    isiyle
    0.06
    _processed
    0.06
    "%(
    0.06
     profess
    0.06
    ("");
    0.06
    (DWORD
    0.06
    timeline
    0.06
    ỹ
    0.06
    upported
    0.06
    Activations Density 0.041%

    No Known Activations