© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 105062
    Prev
    Next
    INDEX
    Explanations

    tumor

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     posi
    -0.08
    _ly
    -0.07
    Craft
    -0.07
     practices
    -0.07
     seals
    -0.07
     WRITE
    -0.07
     relations
    -0.07
     wielding
    -0.07
    actly
    -0.06
     chase
    -0.06
    POSITIVE LOGITS
     Mur
    0.08
     tumor
    0.08
    _ER
    0.08
     tumors
    0.07
    };
↵
↵
↵
    0.07
     mur
    0.07
    ]|
    0.06
    623
    0.06
    .tree
    0.06
    	Il
    0.06
    Activations Density 0.014%

    No Known Activations