© 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. 108959
    Prev
    Next
    INDEX
    Explanations

    people's contributions

    np_max-act · gemini-2.0-flash

    The neuron never activates (all token activations are zero), i.e. it doesn’t respond to any text feature.

    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
    HOOK
    -0.07
    阅读次数
    -0.06
     cessation
    -0.06
     bowel
    -0.06
     tôn
    -0.06
    aran
    -0.06
     respectfully
    -0.06
    _read
    -0.06
     Resolve
    -0.06
    krit
    -0.06
    POSITIVE LOGITS
    شر
    0.07
    UIStoryboardSegue
    0.07
    PackageManager
    0.06
    学生
    0.06
    returnValue
    0.06
    .PropertyType
    0.06
    .Abs
    0.06
    _MS
    0.06
    itech
    0.06
    .ViewModel
    0.06
    Activations Density 0.052%

    No Known Activations