© 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. 27195
    Prev
    Next
    INDEX
    Explanations

    legal terminologies and references

    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
    ikip
    -0.06
    egt
    -0.06
    erse
    -0.06
    ersions
    -0.06
    IDEOS
    -0.05
     u
    -0.05
     Runnable
    -0.05
    .slides
    -0.05
    .ca
    -0.05
    Unmount
    -0.05
    POSITIVE LOGITS
     EU
    0.09
    EU
    0.08
    krom
    0.08
     Eu
    0.08
    eu
    0.08
    adil
    0.08
    vo
    0.07
     europ
    0.07
     european
    0.07
     European
    0.07
    Activations Density 0.003%

    No Known Activations