© 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. 90747
    Prev
    Next
    INDEX
    Explanations

    Accepting or rejecting

    np_max-act · gemini-2.0-flash

    This neuron responds to mentions of accepting or declining offers (e.g. “accepting,” “turned down,” “offer”).

    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
     propagation
    -0.08
     Editors
    -0.08
     Beast
    -0.07
    An
    -0.07
     Reign
    -0.07
     Rational
    -0.06
     Rigidbody
    -0.06
    集合
    -0.06
    icom
    -0.06
    Ant
    -0.06
    POSITIVE LOGITS
     seiz
    0.07
     υπ
    0.06
    .defineProperty
    0.06
     düz
    0.06
     enthusiastically
    0.06
    {{--
    0.06
    mons
    0.06
    reh
    0.06
     accepting
    0.06
    �
    0.06
    Activations Density 0.019%

    No Known Activations