© 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
    4. Resid Post - 131k
    5. 27-RESID-POST-AA
    6. 104111
    Prev
    Next
    INDEX
    Explanations

    now

    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_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Follow
    -0.08
    ↵
    -0.07
    ?',
    -0.07
     رسول
    -0.07
     aggressively
    -0.07
     myslí
    -0.07
    Visualization
    -0.07
    daily
    -0.06
    (ignore
    -0.06
     Readonly
    -0.06
    POSITIVE LOGITS
    SKTOP
    0.07
     chap
    0.07
    evity
    0.06
     hoops
    0.06
     browse
    0.06
    cole
    0.06
    _mv
    0.06
    croft
    0.06
    úb
    0.06
    аксим
    0.06
    Activations Density 0.190%

    No Known Activations