© 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. 106430
    Prev
    Next
    INDEX
    Explanations

    mentions of availability in various contexts

    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
    perature
    -0.08
    ниÑĨе
    -0.06
    ugo
    -0.06
    elsinki
    -0.06
    awan
    -0.06
    avy
    -0.06
    bsite
    -0.06
    pons
    -0.06
    .CopyTo
    -0.06
    ÑĪев
    -0.06
    POSITIVE LOGITS
    OffsetTable
    0.07
    ä½Ĩ
    0.07
     exclusively
    0.07
     ragaz
    0.07
    ISTA
    0.06
     Trap
    0.06
    åĸĦ
    0.06
     separately
    0.06
    нÑı
    0.06
    ektir
    0.06
    Activations Density 0.014%

    No Known Activations