© 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
    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. 6165
    Prev
    Next
    INDEX
    Explanations

    folder

    np_max-act · gemini-2.0-flash

    technical details related to image annotations and metadata.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on XML/HTML-style metadata tag names (e.g. folder, source, filename)—i.e. it detects the presence of markup tags.

    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
     включ
    -0.06
    ollah
    -0.06
    }&
    -0.06
    cur
    -0.06
    utsch
    -0.06
     reversed
    -0.06
     далі
    -0.06
     کیفیت
    -0.06
     runner
    -0.06
     HashMap
    -0.06
    POSITIVE LOGITS
     keto
    0.07
     Middleware
    0.07
     minority
    0.07
     moyen
    0.06
    ersistent
    0.06
     mô
    0.06
     essentials
    0.06
     hton
    0.06
    .readdir
    0.06
    /cpp
    0.06
    Activations Density 0.001%

    No Known Activations