© 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. 15-LLAMASCOPE-RES-131K
    11. 87675
    Prev
    Next
    INDEX
    Explanations

    keywords related to notable achievements or milestones of individuals

    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
    _coverage
    -0.06
    ierrez
    -0.06
    aurant
    -0.06
     horns
    -0.06
    Bookmark
    -0.06
    odied
    -0.06
    .SwingConstants
    -0.06
    ourn
    -0.06
    onto
    -0.06
    atoria
    -0.05
    POSITIVE LOGITS
    IMAL
    0.08
    ALLE
    0.07
    ulf
    0.06
    ramer
    0.06
    .mdl
    0.06
    alle
    0.06
    _INCREMENT
    0.06
    ulur
    0.06
    ensi
    0.06
    ìĤ°
    0.06
    Activations Density 0.007%

    No Known Activations