© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 68805
    Prev
    Next
    INDEX
    Explanations

    more than just

    np_max-act · gemini-2.0-flash

    The neuron detects comparative or emphatic “more than…” constructions (e.g. “more than just…”/“much more…”).

    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
     हट
    -0.07
    อำนวย
    -0.07
    "My
    -0.06
    Dir
    -0.06
     muttered
    -0.06
     मश
    -0.06
     devam
    -0.06
     kron
    -0.06
     newborn
    -0.06
     todd
    -0.06
    POSITIVE LOGITS
     šk
    0.06
    :'',
    0.06
    .Are
    0.06
    得到
    0.06
    	ar
    0.06
     Calif
    0.06
    .URI
    0.06
     Ill
    0.06
    nown
    0.06
     động
    0.06
    Activations Density 0.042%

    No Known Activations