© 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. 15-RESID-POST-AA
    6. 59018
    Prev
    Next
    INDEX
    Explanations

    code

    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
    NSS
    -0.06
    standard
    -0.06
     Lease
    -0.06
    	status
    -0.06
     impeachment
    -0.06
    企業
    -0.06
     апп
    -0.06
    ubic
    -0.06
     �
    -0.06
     masks
    -0.06
    POSITIVE LOGITS
     rulings
    0.07
    ([
    ↵
    0.07
    aclass
    0.07
    Journal
    0.06
    :white
    0.06
    _FOUND
    0.06
     torrent
    0.06
     consecutive
    0.06
    _tac
    0.06
    (lua
    0.06
    Activations Density 0.015%

    No Known Activations