© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 66309
    Prev
    Next
    INDEX
    Explanations

    supplementary article text

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     slips
    -0.07
     shadows
    -0.07
     fading
    -0.07
     intensity
    -0.07
     plaintiff
    -0.06
    )\<
    -0.06
    097
    -0.06
     SC
    -0.06
    (\
    -0.06
     SUN
    -0.06
    POSITIVE LOGITS
    	prev
    0.06
    _done
    0.06
    PC
    0.06
    lian
    0.06
     Representatives
    0.06
     BOOL
    0.06
     argv
    0.06
     occurs
    0.06
     comply
    0.06
     Movement
    0.05
    Activations Density 0.015%

    No Known Activations