© 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. 94669
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the importance and requirements of documentation and records in various contexts

    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
    oot
    -0.08
    osas
    -0.07
    æ¡
    -0.07
    eyen
    -0.06
    浩
    -0.06
    criptive
    -0.06
    ridged
    -0.06
    idata
    -0.06
    vard
    -0.06
    å¼ĺ
    -0.06
    POSITIVE LOGITS
     presence
    0.07
    presence
    0.06
    ayment
    0.06
    ayload
    0.06
    766
    0.06
    upy
    0.06
     provision
    0.06
    yz
    0.06
     courts
    0.06
    730
    0.06
    Activations Density 0.023%

    No Known Activations