© 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. 25216
    Prev
    Next
    INDEX
    Explanations

    procedures and operations

    np_max-act · gemini-2.0-flash

    references to technical specifications and methods related to electronic communication systems.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    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
    _el
    -0.07
    어진
    -0.06
    ERC
    -0.06
    Rew
    -0.06
    Alexander
    -0.06
    Next
    -0.06
    lasting
    -0.06
    unc
    -0.06
    Unc
    -0.06
     isnt
    -0.06
    POSITIVE LOGITS
     underway
    0.07
     "('
    0.07
    _country
    0.06
    <title
    0.06
     màu
    0.06
    mast
    0.06
     Canon
    0.06
    	container
    0.06
     CONDITION
    0.06
     注意
    0.06
    Activations Density 0.097%

    No Known Activations