© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 18129
    Prev
    Next
    INDEX
    Explanations

    Java code

    np_max-act · gemini-2.0-flash

    Java class and package definitions related to neural network libraries or frameworks.

    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
     JUL
    -0.08
    음을
    -0.07
     fst
    -0.07
    GST
    -0.07
    .WEST
    -0.07
     웨
    -0.07
     WR
    -0.07
    flt
    -0.06
    ule
    -0.06
    	from
    -0.06
    POSITIVE LOGITS
    ①
    0.06
    Kitchen
    0.06
    ย
    0.06
    es
    0.06
    ças
    0.06
     предус
    0.06
    ;s
    0.06
    848
    0.06
    atural
    0.06
    ②
    0.06
    Activations Density 0.003%

    No Known Activations