© 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. 11-RESID-POST-AA
    6. 125034
    Prev
    Next
    INDEX
    Explanations

    items/objects

    np_max-act · gemini-2.0-flash

    This neuron detects the token "it," as in the “s/it” unit (iterations) shown in the tqdm progress‐bar output.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ental
    -0.07
    };
    ↵
    ↵
    -0.06
    Hall
    -0.06
     Video
    -0.06
     Rachel
    -0.06
     brown
    -0.06
    스토
    -0.06
     NU
    -0.06
     
    -0.06
     gir
    -0.06
    POSITIVE LOGITS
    _OCC
    0.07
    PDOException
    0.07
    .Filters
    0.06
     Overflow
    0.06
     XP
    0.06
     Essays
    0.06
     трех
    0.06
    empor
    0.06
     Hij
    0.06
    =obj
    0.06
    Activations Density 0.068%

    No Known Activations