© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 13655
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    The neuron fires on spatial‐location phrases describing things on “opposite sides of” something.

    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
    Richard
    -0.08
     internship
    -0.08
    Collect
    -0.07
    投注
    -0.07
     ominous
    -0.07
    Root
    -0.06
    _int
    -0.06
    bitcoin
    -0.06
    -feedback
    -0.06
    徐
    -0.06
    POSITIVE LOGITS
     Kanunu
    0.06
     aktar
    0.06
    .LayoutInflater
    0.06
    κά
    0.06
    zte
    0.06
    EMPLATE
    0.06
    бом
    0.06
    :"-
    0.06
     kapsamında
    0.06
     karşısında
    0.06
    Activations Density 0.012%

    No Known Activations