© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 74641
    Prev
    Next
    INDEX
    Explanations

    Chemistry

    np_max-act · gemini-2.0-flash

    The neuron is detecting mentions of redox‐active chemical species and cofactors (e.g. Fe(II)/ferrous iron, hydroquinone/quinone, ascorbate, reducing compounds) that participate in oxidation–reduction reactions.

    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
     suites
    -0.07
     extraction
    -0.07
     Extraction
    -0.06
     Area
    -0.06
     alto
    -0.06
     aider
    -0.06
    educ
    -0.06
    .FloatField
    -0.06
    icrosoft
    -0.06
    byterian
    -0.06
    POSITIVE LOGITS
    그러
    0.08
    应当
    0.07
    详情
    0.07
    belum
    0.06
    bug
    0.06
    시에
    0.06
     shooter
    0.06
     skal
    0.06
    är
    0.06
     violating
    0.06
    Activations Density 0.042%

    No Known Activations