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. 19-RESID-POST-AA
    6. 30131
    Prev
    Next
    INDEX
    Explanations

    Personal narratives

    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
     Brass
    -0.07
    (dataSource
    -0.07
    동안
    -0.06
    LiveData
    -0.06
     首页第
    -0.06
    isible
    -0.06
     boyunca
    -0.06
     supplemented
    -0.06
    <Action
    -0.06
    َه
    -0.06
    POSITIVE LOGITS
    ayscale
    0.07
    tick
    0.07
    _prod
    0.07
     dominant
    0.07
     editor
    0.07
    basic
    0.06
     isempty
    0.06
    }px
    0.06
     Snapshot
    0.06
     Куб
    0.06
    Activations Density 0.016%

    No Known Activations