© 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
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 18308
    Prev
    Next
    INDEX
    Explanations

    It detects numeric mentions that quantify people or personnel (counts of crew, workers, residents, employees, etc.).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    σον
    -0.07
    -headed
    -0.07
    }'
    -0.07
     save
    -0.07
    ailed
    -0.07
     encoder
    -0.06
     }
    -0.06
     Bullet
    -0.06
     heuristic
    -0.06
     TERMIN
    -0.06
    POSITIVE LOGITS
     blanco
    0.06
    interested
    0.06
     rapidement
    0.06
     Nimbus
    0.06
    	users
    0.05
     помогает
    0.05
    .gallery
    0.05
     builder
    0.05
    		      
    0.05
    рал
    0.05
    Activations Density 0.138%

    No Known Activations