© 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. 19-RESID-POST-AA
    6. 58846
    Prev
    Next
    INDEX
    Explanations

    the

    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
    doing
    -0.08
    notin
    -0.07
    โค
    -0.07
     побач
    -0.07
     literal
    -0.07
    .sha
    -0.07
     seafood
    -0.06
    _wrapper
    -0.06
    .Mark
    -0.06
     encompass
    -0.06
    POSITIVE LOGITS
    олот
    0.08
     demographic
    0.06
    	es
    0.06
    (message
    0.06
    poser
    0.06
     Context
    0.06
    ighest
    0.06
     antique
    0.06
     banker
    0.06
     Golden
    0.06
    Activations Density 0.005%

    No Known Activations