Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 42501
    Prev
    Next
    INDEX
    Explanations

    code comments and edits

    np_max-act · gemini-2.0-flash

    commands or instructions related to code execution and system interaction.

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

    The neuron detects when an answer cites or attributes a point to another user (e.g. “@username pointed out in the comments”).

    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
    eted
    -0.07
    umes
    -0.06
    .assertRaises
    -0.06
     ske
    -0.06
    ơm
    -0.06
     Sims
    -0.06
    วง
    -0.06
     Carm
    -0.06
     writ
    -0.06
    ahat
    -0.06
    POSITIVE LOGITS
    DOCTYPE
    0.08
     Barry
    0.07
     bowl
    0.07
    _Db
    0.07
     Exercises
    0.06
    interopRequireDefault
    0.06
    Increase
    0.06
     commit
    0.06
     Linux
    0.06
     crusher
    0.06
    Activations Density 0.022%

    No Known Activations