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. 27-RESID-POST-AA
    6. 9978
    Prev
    Next
    INDEX
    Explanations

    Legal proceedings involving juries

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .getIndex
    -0.07
    cisi
    -0.06
    (Canvas
    -0.06
     Recommendations
    -0.06
    _setup
    -0.06
     revisit
    -0.06
    west
    -0.06
    Fore
    -0.06
     noted
    -0.06
    apatkan
    -0.06
    POSITIVE LOGITS
     Discuss
    0.06
     příjem
    0.06
     Clarence
    0.06
     سابق
    0.06
    _PRESENT
    0.06
     Penal
    0.06
    천
    0.06
    نز
    0.06
    biên
    0.06
     obedience
    0.06
    Activations Density 0.008%

    No Known Activations