Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 41863
    Prev
    Next
    INDEX
    Explanations

    Descriptive/opinionated writing

    np_max-act · gemini-2.0-flash

    This neuron fires strongly on longer, content-bearing words (i.e. non-function, domain-specific terms) rather than on short or common words.

    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
     meg
    -0.07
     PAD
    -0.07
     сум
    -0.06
    itti
    -0.06
    설
    -0.06
     melan
    -0.06
     presume
    -0.06
    _POL
    -0.06
    .HCM
    -0.06
    实
    -0.06
    POSITIVE LOGITS
    ;amp
    0.08
    Units
    0.07
    -bootstrap
    0.07
     QDateTime
    0.07
     barn
    0.07
    	sm
    0.07
     đề
    0.06
     (^
    0.06
    ární
    0.06
    
    ↵
    
    ↵
    0.06
    Activations Density 0.136%

    No Known Activations