© 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. 71224
    Prev
    Next
    INDEX
    Explanations

    the word "in" and its various contexts within the document

    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
    isha
    -0.07
    OperationException
    -0.07
    å½¹
    -0.06
    iesel
    -0.06
    odata
    -0.06
    eru
    -0.06
    boom
    -0.06
    нÑĤ
    -0.06
    erna
    -0.06
    outu
    -0.06
    POSITIVE LOGITS
    lli
    0.07
     Elliot
    0.07
     Elliott
    0.07
     unc
    0.07
     intercept
    0.07
    abcdefghijklmnop
    0.06
    )?$
    0.06
    ForMember
    0.06
    orgia
    0.06
    --------------------------------------------------------------------------↵
    0.06
    Activations Density 0.006%

    No Known Activations