© 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. 30411
    Prev
    Next
    INDEX
    Explanations

    hope

    np_max-act · gemini-2.0-flash

    The neuron primarily responds to explicit expressions of positive outlook—most strongly to the words “hope” and “optimism.”

    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
     div
    -0.07
    姉
    -0.06
    .mix
    -0.06
     med
    -0.06
     gut
    -0.06
    drm
    -0.06
    ạ
    -0.06
     Bell
    -0.06
    level
    -0.06
    อะไร
    -0.06
    POSITIVE LOGITS
     hope
    0.12
     Hope
    0.10
     hopeful
    0.09
    Hope
    0.09
    uí
    0.07
     optimism
    0.07
    oreal
    0.07
     Spokane
    0.07
     menace
    0.07
    WA
    0.07
    Activations Density 0.010%

    No Known Activations