© 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. 17-LLAMASCOPE-RES-131K
    11. 127359
    Prev
    Next
    INDEX
    Explanations

    themes of survival and resilience in the face of adversity

    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
    .mybatis
    -0.07
    buz
    -0.07
    eldo
    -0.07
    afd
    -0.07
    lacak
    -0.07
    ÑĢиз
    -0.06
     cap
    -0.06
    ertiary
    -0.06
    åħ¨åĽ½
    -0.06
    _SF
    -0.06
    POSITIVE LOGITS
    ifen
    0.07
     mime
    0.07
     privileges
    0.07
     priv
    0.07
     forbidden
    0.06
     morale
    0.06
    priv
    0.06
     survival
    0.06
     daily
    0.06
     unofficial
    0.06
    Activations Density 0.010%

    No Known Activations