© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 123448
    Prev
    Next
    INDEX
    Explanations

    references to academic papers and citations

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    jam
    -0.07
    255
    -0.07
    ĶåĽŀ
    -0.07
    oram
    -0.07
    [of
    -0.06
    ------+
    -0.06
     Truy
    -0.06
    214
    -0.06
    asse
    -0.06
    KER
    -0.06
    POSITIVE LOGITS
     various
    0.08
     напÑĢимеÑĢ
    0.08
    ?,?,?,?,
    0.07
     napÅĻ
    0.07
     examples
    0.07
    :
    0.07
     ÅŁun
    0.07
     assorted
    0.07
     ranging
    0.07
    etler
    0.06
    Activations Density 0.038%

    No Known Activations