© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 68836
    Prev
    Next
    INDEX
    Explanations

    mathematical operations

    np_max-act · gemini-2.0-flash

    This neuron is effectively inactive (a “dead” neuron) and does not respond to any tokens.

    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
     Joseph
    -0.06
    modes
    -0.06
    -produced
    -0.06
     Russo
    -0.06
     싱
    -0.06
    傳
    -0.06
    (pop
    -0.06
    RunWith
    -0.06
     Speech
    -0.06
    .pixel
    -0.06
    POSITIVE LOGITS
     primeiro
    0.07
    fix
    0.07
     relacion
    0.06
     speedy
    0.06
     chặt
    0.06
    TextBoxColumn
    0.06
    ão
    0.06
    ovět
    0.06
    ンバ
    0.06
    omy
    0.06
    Activations Density 0.005%

    No Known Activations