© 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. 7-RESID-POST-AA
    6. 27859
    Prev
    Next
    INDEX
    Explanations

    consistently

    np_max-act · gemini-2.0-flash
    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
    achten
    -0.07
     antigen
    -0.07
     folklore
    -0.07
     much
    -0.06
     subst
    -0.06
     має
    -0.06
    	children
    -0.06
     atmos
    -0.06
     parser
    -0.06
     charge
    -0.06
    POSITIVE LOGITS
     consistently
    0.11
     repeatedly
    0.08
     continually
    0.07
    eted
    0.06
     Rob
    0.06
    _Surface
    0.06
     routinely
    0.06
     repeated
    0.06
     numerous
    0.06
     JMP
    0.06
    Activations Density 0.013%

    No Known Activations