© 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. 8771
    Prev
    Next
    INDEX
    Explanations

    travel descriptions

    np_max-act · gemini-2.0-flash

    The neuron identifies verbs and verb phrases that express planning, decision, or intent (e.g. “planned,” “determined,” “deciding to,” “ditch­ing,” etc.).

    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
     rude
    -0.08
    虎
    -0.07
     ties
    -0.06
    ↵		↵
    -0.06
    atic
    -0.06
    iro
    -0.06
     mig
    -0.06
    control
    -0.06
     ideologies
    -0.06
     irritated
    -0.06
    POSITIVE LOGITS
     Bundle
    0.07
    .Active
    0.06
     FontWeight
    0.06
    	free
    0.06
    матрива
    0.06
    CONN
    0.06
    EntryPoint
    0.06
    -rating
    0.06
    .putText
    0.06
    antd
    0.06
    Activations Density 0.020%

    No Known Activations