© 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. 15-RESID-POST-AA
    6. 84665
    Prev
    Next
    INDEX
    Explanations

    rad

    np_max-act · gemini-2.0-flash

    mentions of phase, cycle, or other timing/oscillation-related terms (e.g., phase, peak, node, cycle, midstance).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     petits
    -0.07
    Annotations
    -0.07
    Constants
    -0.07
     organisation
    -0.07
    ues
    -0.07
    	                   
    -0.07
     Emerging
    -0.06
    cura
    -0.06
    -frame
    -0.06
    кин
    -0.06
    POSITIVE LOGITS
    iembre
    0.06
    _lm
    0.06
    _KEYWORD
    0.06
    PreparedStatement
    0.06
     DST
    0.06
    .labelControl
    0.06
     císa
    0.06
    URIComponent
    0.06
     sought
    0.06
    withstanding
    0.06
    Activations Density 0.059%

    No Known Activations