© 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. 5836
    Prev
    Next
    INDEX
    Explanations

    technical details and measurements related to audio and microphone systems

    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
    osi
    -0.07
    744
    -0.06
    ittance
    -0.06
     now
    -0.06
     afore
    -0.06
    âĢİ
    -0.06
    aname
    -0.06
     aforementioned
    -0.06
     instead
    -0.05
    itti
    -0.05
    POSITIVE LOGITS
     cÃłng
    0.10
     larger
    0.08
    andalone
    0.08
    è¶Ĭ
    0.07
    iol
    0.07
    iert
    0.07
    larg
    0.07
    ffects
    0.07
     higher
    0.07
     determinant
    0.07
    Activations Density 0.067%

    No Known Activations