© 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. 88990
    Prev
    Next
    INDEX
    Explanations

    stage

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “stage” (or “stages”) when used to label numbered steps in a procedure.

    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
     money
    -0.07
     cannot
    -0.07
     URLs
    -0.06
    weet
    -0.06
     对
    -0.06
     Reeves
    -0.06
     Elliot
    -0.06
     debt
    -0.06
    عود
    -0.06
     correlations
    -0.06
    POSITIVE LOGITS
     stage
    0.14
    Stage
    0.14
     Stage
    0.13
     stages
    0.11
    stage
    0.11
    	stage
    0.10
    -stage
    0.10
    Phase
    0.10
     phases
    0.10
    阶段
    0.09
    Activations Density 0.025%

    No Known Activations