© 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. 9-LLAMASCOPE-RES-131K
    11. 97858
    Prev
    Next
    INDEX
    Explanations

    specific terminology and keywords related to software and technology concepts

    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
    hand
    -0.10
    hol
    -0.10
    hide
    -0.10
    hattan
    -0.09
    hood
    -0.08
    hart
    -0.08
    hit
    -0.08
    half
    -0.08
    haft
    -0.08
    hard
    -0.08
    POSITIVE LOGITS
    ting
    0.17
    ãģĬãĤĬ
    0.12
    ted
    0.12
    iffany
    0.11
    imestep
    0.11
    esseract
    0.11
    umblr
    0.10
    ters
    0.10
    aylor
    0.10
    olkien
    0.10
    Activations Density 1.599%

    No Known Activations