© 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. 27512
    Prev
    Next
    INDEX
    Explanations

    terms related to measurement and evaluation in scientific contexts

    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
    [^
    -0.07
    -
    -0.07
    vez
    -0.06
     singular
    -0.06
    âĢ¦
    -0.06
     bigger
    -0.06
     paramet
    -0.06
    ’
    -0.06
    ..
    -0.06
     –
    -0.06
    POSITIVE LOGITS
    ìn
    0.08
    ñana
    0.08
    .extent
    0.07
    #ad
    0.07
    openid
    0.07
    泡
    0.07
    xies
    0.07
    ÐŁÐļ
    0.07
    âij
    0.07
    itten
    0.07
    Activations Density 0.000%

    No Known Activations