© 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. 73923
    Prev
    Next
    INDEX
    Explanations

    segments of text that refer to portions or sections of content

    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
    yy
    -0.08
    room
    -0.08
    asin
    -0.07
    yan
    -0.07
    eden
    -0.07
    bane
    -0.07
    sed
    -0.07
    ford
    -0.07
    odia
    -0.07
    boy
    -0.07
    POSITIVE LOGITS
    ally
    0.14
    ality
    0.13
    naire
    0.12
    als
    0.12
    ately
    0.10
    naires
    0.10
    ALLY
    0.10
    ary
    0.10
    nage
    0.09
    nel
    0.09
    Activations Density 0.016%

    No Known Activations