© 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. 110103
    Prev
    Next
    INDEX
    Explanations

    alpacas

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the substring “paca,” most prominently picking up the model name “Alpaca.”

    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
    .font
    -0.07
    (lines
    -0.07
    inner
    -0.07
    minute
    -0.07
    INNER
    -0.07
    urpose
    -0.06
    _ring
    -0.06
    =len
    -0.06
     sought
    -0.06
    Inner
    -0.06
    POSITIVE LOGITS
    cco
    0.08
     Cay
    0.07
    pal
    0.06
    нообраз
    0.06
     á
    0.06
    quez
    0.06
    aca
    0.06
    oce
    0.06
    -c
    0.06
     IPCC
    0.06
    Activations Density 0.002%

    No Known Activations