© 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. 92081
    Prev
    Next
    INDEX
    Explanations

    offset

    np_max-act · gemini-2.0-flash

    The neuron activates on text about carbon neutrality and carbon offsetting.

    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
    CARD
    -0.06
    462
    -0.06
    상담
    -0.06
     hộp
    -0.06
     hôm
    -0.06
    stateParams
    -0.06
    _management
    -0.06
     answered
    -0.06
    btn
    -0.06
    ็นอ
    -0.06
    POSITIVE LOGITS
    -buy
    0.07
    :*
    0.07
    JI
    0.06
     шир
    0.06
    ]int
    0.06
     поверхность
    0.06
     theoretically
    0.06
     overlay
    0.06
    ;l
    0.06
     específ
    0.06
    Activations Density 0.006%

    No Known Activations