© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 35122
    Prev
    Next
    INDEX
    Explanations

    Text processing

    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
    -aff
    -0.07
     Shows
    -0.06
    ROOM
    -0.06
    capt
    -0.06
     stride
    -0.06
     GPL
    -0.06
     eclipse
    -0.06
    ography
    -0.06
     empleado
    -0.06
     coke
    -0.06
    POSITIVE LOGITS
    ाइ
    0.08
     -*-↵↵
    0.07
    .evaluate
    0.07
     bothered
    0.07
     miktar
    0.07
    []>(
    0.07
    (Symbol
    0.07
    成了
    0.06
     objectAtIndex
    0.06
     archival
    0.06
    Activations Density 0.012%

    No Known Activations