© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 129740
    Prev
    Next
    INDEX
    Explanations

    Technical/code documentation

    np_max-act · gemini-2.0-flash

    finds numeric tokens (numbers and numeric values) in the text.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
    ']];↵
    -0.07
     вули
    -0.06
     Grad
    -0.06
    يلاد
    -0.06
     vše
    -0.06
    }],
    -0.06
     })),↵
    -0.06
    '][$
    -0.06
     }]);↵
    -0.06
     Chim
    -0.06
    POSITIVE LOGITS
    ,x
    0.06
     Lance
    0.06
     HF
    0.06
    REMOTE
    0.06
     privacy
    0.06
    &T
    0.06
    ForObject
    0.06
     sexy
    0.06
    terior
    0.06
    鳥
    0.06
    Activations Density 0.000%

    No Known Activations