© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 95411
    Prev
    Next
    INDEX
    Explanations

    mentions of interventions, particularly in relation to personal challenges or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Insensitive
    -0.09
    elik
    -0.09
    Disappear
    -0.08
    adla
    -0.08
    sik
    -0.08
    _unsigned
    -0.08
    .datas
    -0.07
    ¸ı
    -0.07
    Scalars
    -0.07
    окол
    -0.07
    POSITIVE LOGITS
     lies
    0.06
    quet
    0.06
    zer
    0.06
    101
    0.05
    \
    0.05
    372
    0.05
     Lamp
    0.05
     ti
    0.05
     stitches
    0.05
     rightly
    0.05
    Activations Density 0.002%

    No Known Activations