© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 104454
    Prev
    Next
    INDEX
    Explanations

    connections and comparisons within data or arguments

    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
    ares
    -0.07
    sea
    -0.06
    aits
    -0.06
    imore
    -0.06
    .async
    -0.06
    irá
    -0.06
    æ°Ĺãģ«åħ¥
    -0.06
    ëĤ
    -0.06
    PLL
    -0.06
    LLU
    -0.06
    POSITIVE LOGITS
     expected
    0.27
    expected
    0.23
     Expected
    0.22
    Expected
    0.20
    (expected
    0.18
     EXPECT
    0.18
    _expected
    0.17
     expect
    0.16
    EXPECTED
    0.16
     expectedResult
    0.16
    Activations Density 0.054%

    No Known Activations