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. 7-RESID-POST-AA
    6. 21459
    Prev
    Next
    INDEX
    Explanations

    talking about their day

    np_max-act · gemini-2.0-flash

    passages describing everyday family/domestic interactions and caregiving (home life, parents/children, daily routines, and intimate conversational support).

    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
     proportions
    -0.08
     WATER
    -0.07
    .ttf
    -0.07
    Lifecycle
    -0.07
    appropriate
    -0.07
    Several
    -0.06
    	page
    -0.06
    !
    -0.06
     Stern
    -0.06
     двад
    -0.06
    POSITIVE LOGITS
     tě
    0.07
     tecr
    0.06
    자기
    0.06
     işlet
    0.06
    Enterprise
    0.06
    IconModule
    0.06
     testimon
    0.06
    161
    0.06
     těž
    0.06
    лися
    0.06
    Activations Density 0.159%

    No Known Activations