© 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. 7-RESID-POST-AA
    11. 81013
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    mentions of hallucinogenic drugs, narcotics, or related drug terms.

    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
     blackmail
    -0.07
     actionBar
    -0.06
    θερ
    -0.06
     OECD
    -0.06
    *&
    -0.06
     охорони
    -0.06
     trophy
    -0.06
     rainfall
    -0.06
     Chore
    -0.06
     COL
    -0.06
    POSITIVE LOGITS
     distinctive
    0.07
    ↵			↵
    0.07
     buộc
    0.06
    'être
    0.06
    .DrawString
    0.06
                            
↵
    0.06
    kladní
    0.06
    ½
    0.06
     送
    0.06
     batter
    0.06
    Activations Density 0.001%

    No Known Activations