Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 23-RESID-POST-AA
    6. 103823
    Prev
    Next
    INDEX
    Explanations

    algorithms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ीक
    -0.07
     WHAT
    -0.07
    next
    -0.07
    NP
    -0.07
    earing
    -0.07
    Going
    -0.07
     sticker
    -0.07
     bean
    -0.07
     traitement
    -0.06
     Stanton
    -0.06
    POSITIVE LOGITS
    ΟΛ
    0.06
     Μον
    0.06
    -defense
    0.05
    	endif
    0.05
     inhibit
    0.05
    `"]↵
    0.05
     indo
    0.05
    _policy
    0.05
    ρκ
    0.05
     awareness
    0.05
    Activations Density 0.004%

    No Known Activations