© 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. 71112
    Prev
    Next
    INDEX
    Explanations

    occurrences of company names or formal business designations

    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
    atel
    -0.07
    vester
    -0.07
    iel
    -0.07
    berman
    -0.06
    ÃŁen
    -0.06
    esteem
    -0.06
    .opensource
    -0.06
    oster
    -0.06
    eyer
    -0.06
    zet
    -0.06
    POSITIVE LOGITS
    alloca
    0.07
    poi
    0.06
    hetto
    0.06
    inizi
    0.06
    ersh
    0.06
     æģ
    0.06
     Halo
    0.06
    ç§
    0.06
     )))
    0.06
     Lug
    0.05
    Activations Density 0.000%

    No Known Activations