© 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. 73690
    Prev
    Next
    INDEX
    Explanations

    hexadecimal representations and technical terms related to software or coding

    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
     unf
    -0.05
    ambiguous
    -0.05
    iser
    -0.05
    asco
    -0.05
    401
    -0.05
     pag
    -0.05
    108
    -0.05
     aspect
    -0.05
    et
    -0.05
    aux
    -0.05
    POSITIVE LOGITS
    ÑĢаз
    0.09
    mpl
    0.07
     ifndef
    0.07
    ¶Į
    0.07
    pper
    0.07
    èľĺèĽĽ
    0.07
     Exped
    0.07
    ẩn
    0.07
    }elseif
    0.07
    _deinit
    0.07
    Activations Density 0.033%

    No Known Activations