© 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
    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. 55920
    Prev
    Next
    INDEX
    Explanations

    om

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of film directors’ names.

    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
    	results
    -0.06
    .inv
    -0.06
    ്�
    -0.06
     limits
    -0.06
    वत
    -0.06
    	for
    -0.06
    раж
    -0.06
    Ranges
    -0.06
    becca
    -0.06
    .parse
    -0.06
    POSITIVE LOGITS
    .directive
    0.07
    Sac
    0.06
    Mac
    0.06
    Oct
    0.06
     tome
    0.06
     Evelyn
    0.06
     Tournament
    0.06
     dismay
    0.06
    UPDATED
    0.06
     clearInterval
    0.06
    Activations Density 0.055%

    No Known Activations