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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 19-RESID-POST-AA
    6. 9832
    Prev
    Next
    INDEX
    Explanations

    "ial" suffix

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     analyzed
    -0.07
     typical
    -0.06
    species
    -0.06
     bob
    -0.06
     конкрет
    -0.06
    crear
    -0.06
     Arctic
    -0.06
     accommodating
    -0.06
    Sony
    -0.06
    “
    -0.06
    POSITIVE LOGITS
    .Promise
    0.08
    览
    0.08
    .Unlock
    0.07
     ArrayBuffer
    0.07
    キー
    0.07
    .Ar
    0.07
    濃
    0.06
    Sure
    0.06
    serter
    0.06
     brainstorm
    0.06
    Activations Density 0.004%

    No Known Activations