© 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. 6547
    Prev
    Next
    INDEX
    Explanations

    '

    np_max-act · gemini-2.0-flash

    descriptive noun phrases that summarize visual attributes in artwork.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron never activates—it does not detect any specific token pattern.

    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
     خدم
    -0.07
    겠습니다
    -0.07
    起こ
    -0.06
     practiced
    -0.06
     Pandora
    -0.06
    charg
    -0.06
     PEN
    -0.06
    PAD
    -0.06
    (conv
    -0.06
     Glock
    -0.06
    POSITIVE LOGITS
     trabajar
    0.06
    -php
    0.06
    gers
    0.06
    .precision
    0.06
    ίσ
    0.06
    цю
    0.06
     distinction
    0.06
    .dm
    0.06
     insecurity
    0.05
    adc
    0.05
    Activations Density 0.046%

    No Known Activations