© 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. 73761
    Prev
    Next
    INDEX
    Explanations

    social media content

    np_max-act · gemini-2.0-flash

    The neuron fires on instructional, second-person guidance phrases—imperative or planning words like “Plan,” “You need,” “consistently post,” etc.

    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
    ible
    -0.07
    ENT
    -0.07
     errorMessage
    -0.07
     sectional
    -0.06
     Data
    -0.06
     municipal
    -0.06
     receipts
    -0.06
    Me
    -0.06
    ictory
    -0.06
    Ele
    -0.06
    POSITIVE LOGITS
    .phoneNumber
    0.07
    leş
    0.07
    	I
    0.07
     krás
    0.07
    declare
    0.07
     gsl
    0.06
    titre
    0.06
    ;");↵
    0.06
    ظر
    0.06
    	typedef
    0.06
    Activations Density 0.044%

    No Known Activations