© 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. 109271
    Prev
    Next
    INDEX
    Explanations

    Hubble

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of the Hubble Space Telescope (e.g. the word “Hubble” and related telescope references).

    oai_token-act-pair · o4-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
     ruining
    -0.07
    ます
    -0.07
    未
    -0.07
    姓
    -0.07
    %;">
    -0.06
    르는
    -0.06
    asting
    -0.06
    동
    -0.06
    .setEmail
    -0.06
     furnish
    -0.06
    POSITIVE LOGITS
     meme
    0.07
    ubble
    0.06
    oglobin
    0.06
     underwater
    0.06
     combined
    0.06
    _MODAL
    0.06
    .StoredProcedure
    0.06
    .Admin
    0.06
     flyer
    0.06
    uzzer
    0.06
    Activations Density 0.001%

    No Known Activations