© 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. 18332
    Prev
    Next
    INDEX
    Explanations

    terms related to proprietary and customized products or techniques

    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
    /examples
    -0.07
    asad
    -0.07
    andin
    -0.07
    upe
    -0.06
    iri
    -0.06
    bru
    -0.06
    enan
    -0.06
    echan
    -0.06
    /moment
    -0.06
    NSS
    -0.06
    POSITIVE LOGITS
     custom
    0.17
     own
    0.16
     proprietary
    0.14
    custom
    0.13
     Custom
    0.12
    Custom
    0.12
     bespoke
    0.12
    _custom
    0.12
     Own
    0.11
    own
    0.11
    Activations Density 0.060%

    No Known Activations