© 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. 7-RESID-POST-AA
    6. 46534
    Prev
    Next
    INDEX
    Explanations

    cue

    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
    нод
    -0.06
    |,↵
    -0.06
    !');↵
    -0.06
    ssize
    -0.06
     metal
    -0.06
    (金
    -0.06
    Addon
    -0.06
    ';↵
    -0.06
     layers
    -0.06
     cohesion
    -0.06
    POSITIVE LOGITS
     cues
    0.09
     Selected
    0.07
     cue
    0.07
    ??
    0.07
     counsel
    0.07
    537
    0.07
     Buenos
    0.07
    无
    0.06
     denial
    0.06
     crowd
    0.06
    Activations Density 0.003%

    No Known Activations