© 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. 41446
    Prev
    Next
    INDEX
    Explanations

    questions regarding motivations and success

    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
    igua
    -0.08
    اÙĬÙĨ
    -0.07
    úb
    -0.07
    ileaks
    -0.07
     proto
    -0.07
    AffineTransform
    -0.06
    ãĥ»ãĥ»ãĥ»↵↵
    -0.06
    isku
    -0.06
    plies
    -0.06
    hei
    -0.06
    POSITIVE LOGITS
    202
    0.07
     listeners
    0.06
    961
    0.06
    YNC
    0.06
     COVID
    0.06
    ìĪ
    0.06
    zc
    0.06
    hoot
    0.06
    128
    0.05
    ync
    0.05
    Activations Density 0.000%

    No Known Activations