© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 42780
    Prev
    Next
    INDEX
    Explanations

    head

    np_max-act · gemini-2.0-flash

    The neuron is looking for occurrences of the list’s head pointer (i.e. the token “head” in linked-list code).

    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
    bx
    -0.07
    好了
    -0.07
    upplier
    -0.07
     tay
    -0.07
    ій
    -0.07
    .Body
    -0.07
    ó
    -0.07
    _mouse
    -0.06
     Mund
    -0.06
    assy
    -0.06
    POSITIVE LOGITS
     interrogation
    0.07
    abby
    0.07
     inconsistency
    0.06
    gers
    0.06
     dumps
    0.06
    hardt
    0.06
     specialization
    0.06
     rapes
    0.06
    .relu
    0.06
    BF
    0.06
    Activations Density 0.012%

    No Known Activations