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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 23-RESID-POST-AA
    6. 104887
    Prev
    Next
    INDEX
    Explanations

    special code characters

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .).↵↵
    -0.07
     getResult
    -0.07
    ________
    -0.06
     دانلود
    -0.06
    (button
    -0.06
     trebuie
    -0.06
    worksheet
    -0.06
     kategor
    -0.06
    }
    ↵
    ↵
    ↵
    -0.06
     Thiên
    -0.06
    POSITIVE LOGITS
     Composer
    0.06
     jose
    0.06
     sweat
    0.06
    .hl
    0.06
    abar
    0.06
    roje
    0.06
    егод
    0.06
    公園
    0.06
    vic
    0.06
    영
    0.06
    Activations Density 0.002%

    No Known Activations