© 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. 29476
    Prev
    Next
    INDEX
    Explanations

    references to scholarly research and analysis

    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
    /backend
    -0.07
    omu
    -0.06
    oki
    -0.06
     definition
    -0.06
     contradiction
    -0.06
    hma
    -0.06
    shal
    -0.06
    quip
    -0.06
    ka
    -0.06
    omor
    -0.06
    POSITIVE LOGITS
    .dds
    0.08
    çĪµ
    0.07
    _ENUM
    0.07
    ãĥªãĥ¼ãĤº
    0.07
     interpret
    0.07
    пÑĢа
    0.06
    .microsoft
    0.06
    upal
    0.06
    ãĥĥãĤ«ãĥ¼
    0.06
    _locator
    0.06
    Activations Density 0.007%

    No Known Activations