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

    Neuronpedia

    Jacobian LensNEW
    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. 11-RESID-POST-AA
    11. 37967
    Prev
    Next
    INDEX
    Explanations

    checksums

    np_max-act · gemini-2.0-flash

    The neuron activates on chunks of hexadecimal hash values (e.g. parts of SHA-512 or SHA-256 checksums).

    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
    ã
    -0.07
    _magic
    -0.07
     спрос
    -0.06
     زندگی
    -0.06
    -neck
    -0.06
     MongoClient
    -0.06
     Remaining
    -0.06
    matcher
    -0.06
    φή
    -0.06
    akan
    -0.06
    POSITIVE LOGITS
     dominating
    0.07
    changes
    0.06
    April
    0.06
     orden
    0.06
    .vo
    0.06
    *",
    0.06
    ....↵↵
    0.06
     geared
    0.06
     alleen
    0.06
     ΑΓ
    0.06
    Activations Density 0.006%

    No Known Activations