© 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. 12257
    Prev
    Next
    INDEX
    Explanations

    latest

    np_max-act · gemini-2.0-flash

    The neuron primarily activates on the adjective “latest” (and closely related terms indicating current or up-to-date information).

    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
     efforts
    -0.07
    guided
    -0.07
    .large
    -0.06
     Chronicle
    -0.06
     attack
    -0.06
     urges
    -0.06
    .high
    -0.06
     bald
    -0.06
    elta
    -0.06
     Acres
    -0.06
    POSITIVE LOGITS
    _datos
    0.06
    _ABI
    0.06
     Apostle
    0.06
    _CUSTOMER
    0.06
    .getCurrentUser
    0.06
     latest
    0.06
     nichts
    0.06
    ایج
    0.06
    licing
    0.06
     постро
    0.06
    Activations Density 0.009%

    No Known Activations