© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 38105
    Prev
    Next
    INDEX
    Explanations

    git branch

    np_max-act · gemini-2.0-flash

    The neuron activates on references to version‐control branches (e.g. “main,” “develop,” “branch,” “master”).

    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
    小姐
    -0.07
     Crit
    -0.07
    ерк
    -0.07
     것도
    -0.06
    		    ↵
    -0.06
    暮
    -0.06
    εν
    -0.06
    展
    -0.06
    徒歩
    -0.06
    .Request
    -0.06
    POSITIVE LOGITS
    .hour
    0.08
    _Account
    0.07
    Directive
    0.07
    _DESTROY
    0.07
    headline
    0.06
    religious
    0.06
     Competitive
    0.06
     research
    0.06
    ############
    0.06
    _hour
    0.06
    Activations Density 0.004%

    No Known Activations