© 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. 89654
    Prev
    Next
    INDEX
    Explanations

    stopwords

    np_max-act · gemini-2.0-flash

    This neuron detects numeric sequences in dotted‐decimal notation, i.e. parts of IP addresses.

    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
    SUP
    -0.06
    existent
    -0.06
     prosperous
    -0.06
    ẫn
    -0.06
     управ
    -0.06
    ニア
    -0.06
     richtig
    -0.06
    ことは
    -0.06
    amburg
    -0.06
    maries
    -0.06
    POSITIVE LOGITS
    _projection
    0.06
    (write
    0.06
    าระ
    0.06
    cls
    0.06
    _filepath
    0.06
    [axis
    0.06
     nebylo
    0.06
    催
    0.06
     огра
    0.06
     isKindOfClass
    0.06
    Activations Density 0.119%

    No Known Activations