© 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. 90818
    Prev
    Next
    INDEX
    Explanations

    Fantasy novels

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of special magical or powerful artifacts (e.g. “artifact,” “Orb,” “glove,” “gemstone”).

    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
    _atoms
    -0.08
    _label
    -0.07
    —from
    -0.06
    veřej
    -0.06
     Tanner
    -0.06
    )new
    -0.06
    repair
    -0.06
    from
    -0.06
    FLICT
    -0.06
    Side
    -0.06
    POSITIVE LOGITS
    ют
    0.07
    +lsi
    0.07
     realiz
    0.06
    益
    0.06
     Autos
    0.06
     останні
    0.06
     Formatting
    0.06
    exampleModalLabel
    0.06
     вниз
    0.06
    яться
    0.06
    Activations Density 0.030%

    No Known Activations