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. 103848
    Prev
    Next
    INDEX
    Explanations

    phones

    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
     taxable
    -0.07
    라는
    -0.07
     gigantic
    -0.07
    tro
    -0.07
     Explain
    -0.06
     uzun
    -0.06
    长
    -0.06
    lain
    -0.06
    greens
    -0.06
    Purpose
    -0.06
    POSITIVE LOGITS
     @_
    0.07
    telefone
    0.06
     filmm
    0.06
    .GridView
    0.06
    	    
    0.06
    (Func
    0.06
     defaults
    0.06
     Alerts
    0.06
    .instances
    0.06
     conforms
    0.06
    Activations Density 0.043%

    No Known Activations