Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 92670
    Prev
    Next
    INDEX
    Explanations

    God/Allah

    np_max-act · gemini-2.0-flash

    This neuron activates on Portuguese words expressing divine eternality—especially terms like “eterno” and “sem fim.”

    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
    Manage
    -0.07
     Manage
    -0.07
     albums
    -0.06
     týd
    -0.06
     Zuk
    -0.06
     登
    -0.06
    .Static
    -0.06
    調
    -0.06
     آز
    -0.06
     spons
    -0.06
    POSITIVE LOGITS
     Hunter
    0.07
    ATER
    0.06
     gover
    0.06
     广
    0.06
     ajust
    0.06
    剧
    0.06
    grep
    0.06
     oldValue
    0.06
    :border
    0.06
    _Enter
    0.06
    Activations Density 0.024%

    No Known Activations