© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 92412
    Prev
    Next
    INDEX
    Explanations

    code comments

    np_max-act · gemini-2.0-flash

    The neuron fires on fragments of MIT‐style license boilerplate (e.g. “deal in the Software without restriction” and comment markers).

    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
     écrit
    -0.07
     rebuild
    -0.06
    ugs
    -0.06
    .coord
    -0.06
     parti
    -0.06
    이크
    -0.06
     práci
    -0.06
     vlan
    -0.06
     Debbie
    -0.06
     hybrids
    -0.06
    POSITIVE LOGITS
    SACTION
    0.07
    _val
    0.07
    esel
    0.06
    Private
    0.06
    =start
    0.06
    logg
    0.06
    -color
    0.06
    coming
    0.06
    室
    0.06
    setCurrent
    0.06
    Activations Density 0.002%

    No Known Activations