© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 76315
    Prev
    Next
    INDEX
    Explanations

    technical/scientific/religious texts

    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
     صاد
    -0.06
     franc
    -0.06
    اير
    -0.06
     سیم
    -0.06
    औ
    -0.06
    KHTML
    -0.06
     až
    -0.05
    博
    -0.05
    ΗΡ
    -0.05
    Inline
    -0.05
    POSITIVE LOGITS
     burn
    0.07
    .mon
    0.07
    illes
    0.07
     Chop
    0.07
     Consultants
    0.06
    νή
    0.06
     Submitted
    0.06
     remain
    0.06
     cuer
    0.06
     चक
    0.06
    Activations Density 0.123%

    No Known Activations