© 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. 73754
    Prev
    Next
    INDEX
    Explanations

    successful

    np_max-act · gemini-2.0-flash

    The neuron specifically detects occurrences of the adjective “successful” (often in success‐related Superlative phrases).

    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
     aisle
    -0.07
     afore
    -0.07
    Given
    -0.06
    328
    -0.06
     gave
    -0.06
     dames
    -0.06
     hovered
    -0.06
     inverse
    -0.06
    -=
    -0.06
    Agregar
    -0.06
    POSITIVE LOGITS
     successful
    0.15
     success
    0.12
     Successful
    0.11
     successfully
    0.11
    successful
    0.11
    Successful
    0.09
     succeed
    0.09
    成功
    0.09
     성공
    0.08
     successes
    0.08
    Activations Density 0.033%

    No Known Activations