© 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. 15-RESID-POST-AA
    11. 29894
    Prev
    Next
    INDEX
    Explanations

    providing help/alternatives

    np_max-act · gemini-2.0-flash

    language that refuses, warns against, or discourages illegal, harmful, or unethical requests (safety/policy responses).

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ındaki
    -0.07
     errs
    -0.06
    	mouse
    -0.06
    	page
    -0.06
    AlmostEqual
    -0.06
    Projectile
    -0.06
    -handed
    -0.06
     Rookie
    -0.06
    -president
    -0.06
     giải
    -0.06
    POSITIVE LOGITS
     đình
    0.07
     verd
    0.07
     стран
    0.07
     накоп
    0.07
     uncert
    0.06
     unequiv
    0.06
    acket
    0.06
    [D
    0.06
    حة
    0.06
     AppConfig
    0.06
    Activations Density 0.066%

    No Known Activations