© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 73742
    Prev
    Next
    INDEX
    Explanations

    mind

    np_max-act · gemini-2.0-flash

    The neuron activates on first-person “I don’t mind…” (or similar “don’t mind”) expressions indicating acceptance or lack of objection.

    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
     potency
    -0.06
     safest
    -0.06
     zero
    -0.06
    -hash
    -0.06
     accru
    -0.06
     Saturn
    -0.06
     جهان
    -0.06
     Superior
    -0.06
     sour
    -0.06
     Anne
    -0.06
    POSITIVE LOGITS
    .MOUSE
    0.07
    OOD
    0.07
    queen
    0.07
     아이콘
    0.07
     mind
    0.07
     Mind
    0.07
     transmissions
    0.07
    ins
    0.06
    Mind
    0.06
    keyboard
    0.06
    Activations Density 0.004%

    No Known Activations