© 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. 880
    Prev
    Next
    INDEX
    Explanations

    reduction

    np_max-act · gemini-2.0-flash

    The neuron detects words that describe actions of reduction or mitigation (e.g. “reducing,” “reduce,” “could be expected to reduce”).

    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
     diploma
    -0.07
     pit
    -0.07
     Pit
    -0.06
     sing
    -0.06
     ANAL
    -0.06
    ndo
    -0.06
    URT
    -0.06
    timer
    -0.06
    _history
    -0.06
     krat
    -0.06
    POSITIVE LOGITS
     어머니
    0.07
     environmentally
    0.07
     mỹ
    0.06
    locking
    0.06
     consolid
    0.06
    λο
    0.06
     มกราคม
    0.06
    .hour
    0.06
    ้าส
    0.06
    ürger
    0.06
    Activations Density 0.200%

    No Known Activations