© 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. 68926
    Prev
    Next
    INDEX
    Explanations

    demonstrated/showed

    np_max-act · gemini-2.0-flash

    The neuron is triggered by mentions of experimental assay procedures and result reporting (e.g. “analysis,” “demonstrated,” “quantitative,” “PCR,” etc.).

    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
    pring
    -0.08
    eters
    -0.07
    increment
    -0.07
    -public
    -0.07
    Purple
    -0.06
     enctype
    -0.06
    skills
    -0.06
    printing
    -0.06
    interpreter
    -0.06
    .books
    -0.06
    POSITIVE LOGITS
     IconButton
    0.06
    のが
    0.06
     参考
    0.06
     garage
    0.06
     будинку
    0.06
    _mtime
    0.06
    .StringVar
    0.06
    _aes
    0.06
    ทอง
    0.06
    芯
    0.06
    Activations Density 0.031%

    No Known Activations