© 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 EvalsExportsAPI 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. 84342
    Prev
    Next
    INDEX
    Explanations

    code-related terminology and comments

    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
    obel
    -0.07
    /Branch
    -0.06
    olik
    -0.06
    å´İ
    -0.06
    725
    -0.06
    bia
    -0.06
    spd
    -0.06
    odyn
    -0.06
    stantiate
    -0.06
     Bran
    -0.06
    POSITIVE LOGITS
    -relative
    0.08
    ád
    0.07
    ŀæĢ§
    0.07
    RelativeTo
    0.07
     CENTER
    0.07
    -anchor
    0.06
    unsch
    0.06
    cers
    0.06
    anchor
    0.06
    Anchor
    0.06
    Activations Density 0.016%

    No Known Activations