© 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. 11-RESID-POST-AA
    6. 25630
    Prev
    Next
    INDEX
    Explanations

    logical arguments

    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
    ensemble
    -0.06
     место
    -0.06
    	as
    -0.06
     sagen
    -0.06
    xde
    -0.06
     deps
    -0.06
    	char
    -0.06
    .Tool
    -0.06
    Hu
    -0.06
     reelection
    -0.06
    POSITIVE LOGITS
    _step
    0.07
     subsequent
    0.07
     çeşit
    0.07
     remotely
    0.06
    =m
    0.06
    蛇
    0.06
    門
    0.06
    HELP
    0.06
     minim
    0.06
    _sku
    0.06
    Activations Density 0.052%

    No Known Activations