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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 57481
    Prev
    Next
    INDEX
    Explanations

    concepts and phrases related to timelessness or enduring qualities

    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
     Khu
    -0.07
    же
    -0.07
    antom
    -0.06
    λÏİ
    -0.06
    ap
    -0.06
     buurt
    -0.06
    apat
    -0.06
    ek
    -0.06
    annes
    -0.06
     Wol
    -0.06
    POSITIVE LOGITS
     classic
    0.08
     classics
    0.07
    ingly
    0.07
    ród
    0.07
    gue
    0.07
    ť
    0.07
    /loose
    0.07
    rored
    0.07
    peon
    0.07
    classic
    0.06
    Activations Density 0.002%

    No Known Activations