© 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 EvalsExportsinterp-engineNEWAPI 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. 58660
    Prev
    Next
    INDEX
    Explanations

    formal writing

    np_max-act · gemini-2.0-flash

    The neuron fires on subword pieces of German-language words, effectively detecting German text.

    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
     знать
    -0.07
     logistics
    -0.07
     weave
    -0.07
     Shadow
    -0.06
     schwar
    -0.06
     Plot
    -0.06
     Neil
    -0.06
     конструкции
    -0.06
     쪽
    -0.06
    ávají
    -0.06
    POSITIVE LOGITS
    $view
    0.08
    _party
    0.07
    _mas
    0.07
    toList
    0.07
    (tuple
    0.06
    _DEPTH
    0.06
    FFF
    0.06
    	hash
    0.06
    ',↵↵
    0.06
    genome
    0.06
    Activations Density 0.103%

    No Known Activations