Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 127397
    Prev
    Next
    INDEX
    Explanations

    control

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of control groups in research study descriptions.

    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
     따라
    -0.07
    setEnabled
    -0.07
     Durant
    -0.06
     đẹp
    -0.06
     almak
    -0.06
    _bp
    -0.06
    quisitions
    -0.06
    .Template
    -0.06
    (reinterpret
    -0.06
    (Seq
    -0.06
    POSITIVE LOGITS
    ivr
    0.07
    jid
    0.07
    Granted
    0.06
    hover
    0.06
     pově
    0.06
    _notes
    0.06
    _sq
    0.06
    heat
    0.06
    .har
    0.06
    .swift
    0.06
    Activations Density 0.008%

    No Known Activations