© 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 (Instruct)
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 95309
    Prev
    Next
    INDEX
    Explanations

    â

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     setInput
    -0.08
    Inf
    -0.07
     зовсім
    -0.07
    تف
    -0.07
    _FOUND
    -0.06
     DFS
    -0.06
    (Z
    -0.06
    (segment
    -0.06
     cellular
    -0.06
     ";↵
    -0.06
    POSITIVE LOGITS
    â
    0.23
     â
    0.22
     Â
    0.12
    Â
    0.12
     câ
    0.10
    ân
    0.08
     î
    0.08
    âr
    0.08
    回
    0.07
    Won
    0.07
    Activations Density 0.006%

    No Known Activations