© 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
    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. 90946
    Prev
    Next
    INDEX
    Explanations

    ref

    np_max-act · gemini-2.0-flash

    The neuron primarily detects in-text citation markers and reference identifiers (e.g. bracketed numbers and related citation tags).

    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
    服务
    -0.07
     دین
    -0.06
    527
    -0.06
    isté
    -0.06
    noon
    -0.06
    آمد
    -0.06
     knot
    -0.06
    ationally
    -0.06
     installing
    -0.06
    pret
    -0.06
    POSITIVE LOGITS
     Booster
    0.07
     cookie
    0.06
    endif
    0.06
    .CLIENT
    0.06
    Cross
    0.06
     nákup
    0.06
     всього
    0.06
     παρα
    0.06
     CHILD
    0.06
     Comple
    0.06
    Activations Density 0.004%

    No Known Activations