© 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. 3-RESID-POST-AA
    11. 121645
    Prev
    Next
    INDEX
    Explanations

    effect

    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
     ims
    -0.07
     Venus
    -0.07
     Smile
    -0.06
     JPanel
    -0.06
    artin
    -0.06
    URN
    -0.06
    ceries
    -0.06
    	buttons
    -0.06
     Rover
    -0.06
     depleted
    -0.06
    POSITIVE LOGITS
     effects
    0.08
     effect
    0.08
     Effects
    0.08
     courts
    0.07
    -effect
    0.07
    effects
    0.07
    /http
    0.07
    featured
    0.06
     impacts
    0.06
    \u
    0.06
    Activations Density 0.025%

    No Known Activations