© 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. 31313
    Prev
    Next
    INDEX
    Explanations

    information related to corporate partnerships and technology initiatives

    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
    boss
    -0.08
    วล
    -0.07
    abant
    -0.07
    boru
    -0.07
     KÄį
    -0.07
    adÃŃ
    -0.07
    gua
    -0.06
    stroy
    -0.06
    Boss
    -0.06
    itm
    -0.06
    POSITIVE LOGITS
     mutual
    0.12
     mutually
    0.09
     Mutual
    0.07
     SHALL
    0.07
     shall
    0.07
    ÙĨØ´
    0.07
    eres
    0.06
    mut
    0.06
     recip
    0.06
    ÑĢÑĥÑĤ
    0.06
    Activations Density 0.018%

    No Known Activations