© 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. 51801
    Prev
    Next
    INDEX
    Explanations

    Scientific research

    np_max-act · gemini-2.0-flash

    specific scientific and technical terminology related to neuroscience and muscle function.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron responds to mentions of neural‐network or neuroanatomical elements (e.g. “neurons,” “network,” “output neurons”).

    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
     emerging
    -0.08
     Located
    -0.07
     autoFocus
    -0.06
     marijuana
    -0.06
     QSize
    -0.06
    _version
    -0.06
    UnitTest
    -0.06
    looking
    -0.06
    Need
    -0.06
    _comm
    -0.06
    POSITIVE LOGITS
     petit
    0.07
     národ
    0.06
    KIT
    0.06
     Song
    0.06
    ileo
    0.06
    ovol
    0.06
     fö
    0.06
     كس
    0.06
     acknowledge
    0.06
     faded
    0.06
    Activations Density 0.232%

    No Known Activations