© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 12758
    Prev
    Next
    INDEX
    Explanations

    disc

    np_max-act · gemini-2.0-flash

    terms related to the comparison and differentiation of similar concepts or terms.

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

    This neuron responds to longer, technical or specialized multisyllabic words (e.g. “amputation,” “silica,” “satirical,” etc.).

    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
     бок
    -0.07
    比
    -0.06
    ोई
    -0.06
     Sunny
    -0.06
     einz
    -0.06
    unsafe
    -0.06
     human
    -0.06
    89
    -0.06
    倒
    -0.06
     applicant
    -0.06
    POSITIVE LOGITS
    _DROP
    0.07
    #create
    0.07
    _Server
    0.07
     เค
    0.07
    (groups
    0.07
    ~":"
    0.06
     jugar
    0.06
     zipfile
    0.06
    clus
    0.06
    .GetText
    0.06
    Activations Density 0.190%

    No Known Activations