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. 15-RESID-POST-AA
    6. 21086
    Prev
    Next
    INDEX
    Explanations

    roundabouts and intersections

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Aless
    -0.08
     Lana
    -0.07
     взрос
    -0.07
     Herm
    -0.07
     sera
    -0.07
    Iran
    -0.07
    ierz
    -0.07
    Ping
    -0.07
    	else
    -0.07
    �
    -0.07
    POSITIVE LOGITS
    ичних
    0.06
    SelfPermission
    0.06
    .setContentType
    0.06
    OutOfRangeException
    0.06
     dùng
    0.06
    (match
    0.06
    —to
    0.06
    زة
    0.06
    soles
    0.06
    Bachelor
    0.06
    Activations Density 0.009%

    No Known Activations