© 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. 15-RESID-POST-AA
    6. 40803
    Prev
    Next
    INDEX
    Explanations

    abbreviations

    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_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
     ecstasy
    -0.07
    interop
    -0.07
     �
    -0.07
     بدون
    -0.06
    گل
    -0.06
    .""
    -0.06
                        
    -0.06
    _Details
    -0.06
     attachments
    -0.06
    (kv
    -0.06
    POSITIVE LOGITS
     mip
    0.06
    cour
    0.06
     [|
    0.06
    isor
    0.06
    aniel
    0.06
    insics
    0.06
     빠
    0.05
    ді
    0.05
     území
    0.05
    emouth
    0.05
    Activations Density 0.092%

    No Known Activations