Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 30238
    Prev
    Next
    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash

    The neuron never activates—it does not respond to any token.

    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
     Nh
    -0.07
    	host
    -0.07
    partment
    -0.06
    比例
    -0.06
    阿
    -0.06
    13
    -0.06
     vtx
    -0.06
     Hint
    -0.06
     okhttp
    -0.06
     Inv
    -0.06
    POSITIVE LOGITS
    侧
    0.06
    网站
    0.06
     Turbo
    0.06
    [Any
    0.06
    ."+
    0.06
     행동
    0.06
    _REPO
    0.06
    	elem
    0.06
    .Assembly
    0.06
     trespass
    0.06
    Activations Density 0.040%

    No Known Activations