© 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. 73786
    Prev
    Next
    INDEX
    Explanations

    blog posts/conversations

    np_max-act · gemini-2.0-flash

    The neuron fires on technical descriptions of a language model’s capabilities or performance (e.g., terms detailing what the model “can do” or how it “performs”).

    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
    Update
    -0.07
    ilenames
    -0.06
     vocabulary
    -0.06
     notorious
    -0.06
    changed
    -0.06
     logs
    -0.06
     sparing
    -0.06
     трудов
    -0.06
     خاک
    -0.06
    aff
    -0.06
    POSITIVE LOGITS
     }}/
    0.07
    [++
    0.07
    derive
    0.07
     району
    0.06
    __/
    0.06
    ImGui
    0.06
    >>::
    0.06
     düşman
    0.06
    <()>
    0.06
    	Entity
    0.06
    Activations Density 0.096%

    No Known Activations