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. 7-RESID-POST-AA
    6. 10564
    Prev
    Next
    INDEX
    Explanations

    file

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Factor
    -0.08
    entarios
    -0.08
    153
    -0.07
     Rate
    -0.06
    -air
    -0.06
    itan
    -0.06
    -host
    -0.06
     bạc
    -0.06
    -stat
    -0.06
    pose
    -0.06
    POSITIVE LOGITS
     nx
    0.07
     ebay
    0.07
     discharged
    0.07
     açıklam
    0.07
     indefinitely
    0.06
     näch
    0.06
     bx
    0.06
     dolor
    0.06
     가격
    0.06
     csrf
    0.06
    Activations Density 0.036%

    No Known Activations