© 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. 643
    Prev
    Next
    INDEX
    Explanations

    -se

    np_max-act · gemini-2.0-flash

    The neuron is essentially dead (it never activates on 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
    dm
    -0.06
     �
    -0.06
    ـل
    -0.06
    、これ
    -0.06
     builders
    -0.06
     Çünkü
    -0.06
     postav
    -0.06
    EFR
    -0.06
    .pick
    -0.06
    D
    -0.06
    POSITIVE LOGITS
    ree
    0.06
    (*
    0.06
    CONDITION
    0.06
    фер
    0.06
     Shipping
    0.06
     testimon
    0.06
    %",
    0.06
    IQUE
    0.06
    }")
    0.06
    줄
    0.06
    Activations Density 0.830%

    No Known Activations