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. 129472
    Prev
    Next
    INDEX
    Explanations

    break

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the verb “break” (e.g. “break,” “breaks”).

    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
     heroes
    -0.08
    -white
    -0.08
    ismatic
    -0.07
     optic
    -0.07
    andidate
    -0.06
    LogLevel
    -0.06
     celebrated
    -0.06
    rogram
    -0.06
     brom
    -0.06
     deductible
    -0.06
    POSITIVE LOGITS
    .blit
    0.06
    oralType
    0.06
     Mona
    0.06
     Mısır
    0.06
     Everett
    0.06
    _CHARS
    0.06
     Memphis
    0.06
    .Intent
    0.06
     imkân
    0.06
    _ATTACK
    0.05
    Activations Density 0.033%

    No Known Activations