© 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. 75128
    Prev
    Next
    INDEX
    Explanations

    top

    np_max-act · gemini-2.0-flash

    rhyming words ending with the sound "up."

    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
    Serializable
    -0.07
     jitter
    -0.07
    immune
    -0.07
     inconsist
    -0.07
    ủy
    -0.07
    (addr
    -0.06
    意义
    -0.06
     persist
    -0.06
     willing
    -0.06
     irregular
    -0.06
    POSITIVE LOGITS
     top
    0.19
     Top
    0.16
     TOP
    0.15
    top
    0.14
    Top
    0.14
    (top
    0.12
    	top
    0.12
    -top
    0.11
    .TOP
    0.11
    _top
    0.11
    Activations Density 0.032%

    No Known Activations