© 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. 77519
    Prev
    Next
    INDEX
    Explanations

    mentions of educational institutions and programs

    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
    atus
    -0.06
    arent
    -0.06
    Č↵
    -0.06
    anut
    -0.06
    äm
    -0.06
     Barker
    -0.06
     Nová
    -0.06
    ache
    -0.05
    avia
    -0.05
    hower
    -0.05
    POSITIVE LOGITS
     NA
    0.07
     Shepard
    0.07
    hev
    0.07
     заÑģÑĤоÑģ
    0.07
    734
    0.06
    inati
    0.06
     DISCLAIM
    0.06
     diversity
    0.06
    tu
    0.06
     Diversity
    0.06
    Activations Density 0.000%

    No Known Activations