© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 109357
    Prev
    Next
    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash

    The neuron detects the common “is a” phrase used in introductory statements—e.g. after a company name when defining what the entity “is a” something.

    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
     twilight
    -0.06
     ripe
    -0.06
     cet
    -0.06
    -tax
    -0.06
    nish
    -0.06
    practice
    -0.06
    wid
    -0.05
    sweet
    -0.05
    았
    -0.05
    _NR
    -0.05
    POSITIVE LOGITS
    REAM
    0.08
    籍
    0.07
    cone
    0.07
     wired
    0.07
    .toCharArray
    0.07
     cellForRowAtIndexPath
    0.06
    ویی
    0.06
    .XRLabel
    0.06
     จำก
    0.06
    ный
    0.06
    Activations Density 0.037%

    No Known Activations