© 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. 17438
    Prev
    Next
    INDEX
    Explanations

    corporate names and entities, particularly in the context of patents or technical documents

    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
    hc
    -0.08
    ifest
    -0.08
    ajo
    -0.08
    cai
    -0.07
    illy
    -0.07
    ibi
    -0.07
    tube
    -0.07
    imity
    -0.07
    alars
    -0.07
    lico
    -0.06
    POSITIVE LOGITS
    /cgi
    0.06
     æij
    0.06
    ires
    0.06
    _party
    0.06
    éĻ
    0.06
    íĨ¤
    0.06
     invent
    0.06
    ì§Ŀ
    0.06
    िण
    0.06
     stup
    0.06
    Activations Density 0.003%

    No Known Activations