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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 85273
    Prev
    Next
    INDEX
    Explanations

    requests, offers, agreements

    np_max-act · gemini-2.0-flash

    The neuron is selectively activated by words announcing extra allowances or extensions—e.g. “additional,” “extension,” “President” (in the context of filing an extension).

    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
    bdd
    -0.07
    	case
    -0.07
     sinks
    -0.07
    저
    -0.06
     网
    -0.06
    881
    -0.06
     final
    -0.06
    焼
    -0.06
    Speech
    -0.06
    โป
    -0.06
    POSITIVE LOGITS
    -Compatible
    0.07
    ']);↵↵
    0.07
    >↵
    0.06
    (attribute
    0.06
     socialism
    0.06
    chl
    0.06
    ाई
    0.06
     nightclub
    0.06
     ).↵↵
    0.06
    -launch
    0.06
    Activations Density 0.195%

    No Known Activations