© 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. 93195
    Prev
    Next
    INDEX
    Explanations

    computer-related processes and comparisons

    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
    ruba
    -0.08
     UNICODE
    -0.07
    \Blueprint
    -0.07
     GENERIC
    -0.07
    ÏĦί
    -0.07
    }elseif
    -0.07
     à¤Ĩव
    -0.07
    oundingBox
    -0.07
    æ³Ľ
    -0.07
    èĮĤ
    -0.07
    POSITIVE LOGITS
    ëĵ¯
    0.07
    Ĥ
    0.07
    -like
    0.06
    845
    0.06
     equivalent
    0.06
    systems
    0.06
     equivalents
    0.06
    oe
    0.06
     Equivalent
    0.06
     systems
    0.06
    Activations Density 0.026%

    No Known Activations