© 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. 93470
    Prev
    Next
    INDEX
    Explanations

    numerical comparisons and changes

    np_max-act · gemini-2.0-flash

    statistical data regarding housing markets and real estate trends.

    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
     scal
    -0.07
    -appointed
    -0.06
    保持
    -0.06
     Urb
    -0.06
    .oc
    -0.06
     divisible
    -0.06
    .biz
    -0.06
     slut
    -0.06
    Mouse
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    	INT
    0.07
     slashes
    0.06
    ULLET
    0.06
     giả
    0.06
     cache
    0.06
    BaseContext
    0.06
     mulher
    0.06
    urchased
    0.06
    입니다
    0.06
    _HEADER
    0.06
    Activations Density 0.014%

    No Known Activations