© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7016
    Prev
    Next
    INDEX
    Explanations

    down

    np_max-act · gemini-2.0-flash

    The neuron is especially sensitive to spatial prepositions/adverbs indicating vertical relation or movement—words like “over” and “down.”

    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
     Jal
    -0.06
    _create
    -0.06
    跑
    -0.06
    _ret
    -0.06
    -fin
    -0.06
     Mitsubishi
    -0.06
     Retro
    -0.06
    Avoid
    -0.06
     Myst
    -0.06
    (category
    -0.06
    POSITIVE LOGITS
    .textBox
    0.08
     شما
    0.07
     coi
    0.07
    етель
    0.07
     sto
    0.07
     ~
    0.07
    :g
    0.06
    minus
    0.06
    cess
    0.06
    	comment
    0.06
    Activations Density 0.004%

    No Known Activations