© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 42541
    Prev
    Next
    INDEX
    Explanations

    abstract

    np_max-act · gemini-2.0-flash

    The neuron activates on terms naming specific cognitive domains or functions (e.g., abstract thinking, reasoning, memory, language, conceptualization) as they arise in neuropsychological or cognitive assessment contexts.

    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
     dark
    -0.07
     rotterdam
    -0.07
     inne
    -0.06
    .after
    -0.06
     TreeNode
    -0.06
     Cindy
    -0.06
    Narrated
    -0.06
     Mand
    -0.06
     Harrison
    -0.06
    .ball
    -0.06
    POSITIVE LOGITS
    _threads
    0.07
    �
    0.07
     násled
    0.06
     scratching
    0.06
    inging
    0.06
    станов
    0.06
    xAD
    0.06
    .foo
    0.06
    ै।↵
    0.06
     versatility
    0.06
    Activations Density 0.021%

    No Known Activations