© 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. 18569
    Prev
    Next
    INDEX
    Explanations

    zucker

    np_max-act · gemini-2.0-flash

    terms related to diseases affecting vision and their underlying mechanisms.

    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
    _profiles
    -0.07
    ampire
    -0.07
    �
    -0.07
    CrLf
    -0.06
    руд
    -0.06
    libraries
    -0.06
    Layout
    -0.06
     Highland
    -0.06
    queueReusableCell
    -0.06
     bulld
    -0.06
    POSITIVE LOGITS
     Canadian
    0.07
     zm
    0.07
     emphasis
    0.06
     Hungary
    0.06
     cn
    0.06
     flurry
    0.06
     Text
    0.06
    メリカ
    0.06
     drew
    0.06
    :“
    0.06
    Activations Density 0.020%

    No Known Activations