© 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. 3850
    Prev
    Next
    INDEX
    Explanations

    statements or mentions of facts

    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
    ULD
    -0.07
    se
    -0.06
    lte
    -0.06
    asser
    -0.06
    ams
    -0.06
     Manson
    -0.06
    emble
    -0.06
    mer
    -0.06
    licher
    -0.06
    .habbo
    -0.06
    POSITIVE LOGITS
     that
    0.09
    itious
    0.09
     bahwa
    0.09
    egasus
    0.08
    that
    0.08
    izr
    0.07
    585
    0.07
    586
    0.07
    avana
    0.07
     fact
    0.07
    Activations Density 0.010%

    No Known Activations