© 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. 104195
    Prev
    Next
    INDEX
    Explanations

    details related to financial assistance programs and their requirements

    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
    alker
    -0.06
     Kash
    -0.06
     modern
    -0.06
     B
    -0.06
    aring
    -0.06
    ãĤ¤ãĥī
    -0.06
     оÑĩ
    -0.06
     N
    -0.06
     acomp
    -0.06
    Scaled
    -0.05
    POSITIVE LOGITS
     participating
    0.08
    ledon
    0.07
    emann
    0.07
    obl
    0.07
    orthand
    0.06
    004
    0.06
    inciple
    0.06
    enheim
    0.06
    ibe
    0.06
     Participation
    0.06
    Activations Density 0.046%

    No Known Activations