© 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. 42694
    Prev
    Next
    INDEX
    Explanations

    folklore creatures

    np_max-act · gemini-2.0-flash

    The neuron activates on descriptive terms in folklore creature definitions—adjectives and nouns that characterize mythical beings (e.g. “supernatural,” “creature,” “spirit,” “playful,” “mischievous,” “shape-shift,” etc.).

    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
     underage
    -0.07
     beam
    -0.07
    ostat
    -0.06
    SPACE
    -0.06
     uží
    -0.06
     rendition
    -0.06
     representation
    -0.06
     composition
    -0.06
     Brooks
    -0.06
     <<<
    -0.06
    POSITIVE LOGITS
     �
    0.07
    .overflow
    0.07
    .person
    0.06
    .increment
    0.06
     kommun
    0.06
    _slug
    0.06
     baş
    0.06
    ίγ
    0.06
    .Emit
    0.06
    _q
    0.06
    Activations Density 0.032%

    No Known Activations