© 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. 106315
    Prev
    Next
    INDEX
    Explanations

    references to historical dates and events

    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
    duit
    -0.08
    ibold
    -0.07
     sovere
    -0.07
     Thief
    -0.07
    GuidId
    -0.07
    DonaldTrump
    -0.06
    ovny
    -0.06
    byss
    -0.06
    357
    -0.06
    ŀæĢ§
    -0.06
    POSITIVE LOGITS
    _DL
    0.08
    .condition
    0.06
    ttp
    0.06
    istrovstvÃŃ
    0.06
     IDirect
    0.06
    .motion
    0.06
    olec
    0.06
    íĴį
    0.06
    uhl
    0.06
    ç²Ĵ
    0.06
    Activations Density 0.047%

    No Known Activations