© 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
    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. 5951
    Prev
    Next
    INDEX
    Explanations

    general descriptions

    np_max-act · gemini-2.0-flash

    The neuron responds to words signaling quantitative or trend‐related discourse—terms like “recently,” “increasingly,” “trend,” “data,” and metric‐oriented verbs that introduce statistics or measurements.

    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
    通過
    -0.06
     лише
    -0.06
     créer
    -0.06
    anc
    -0.06
     desi
    -0.05
    (@"%@",
    -0.05
    .ToTable
    -0.05
     reg
    -0.05
    .City
    -0.05
     legal
    -0.05
    POSITIVE LOGITS
     penetrated
    0.07
    BS
    0.07
     трансп
    0.07
     seizures
    0.07
     و
    0.06
     sunglasses
    0.06
    кар
    0.06
    >';
    0.06
     )
    0.06
    Ge
    0.06
    Activations Density 0.268%

    No Known Activations