© 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. 104171
    Prev
    Next
    INDEX
    Explanations

    numerical values and statistical data related to measurements or categorization

    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
    kud
    -0.07
    辺
    -0.06
    resar
    -0.06
    zu
    -0.06
    åĪĩ
    -0.06
    èŀį
    -0.06
    sea
    -0.06
    _planes
    -0.06
    prim
    -0.06
    ecut
    -0.06
    POSITIVE LOGITS
    де
    0.08
    -star
    0.08
    -HT
    0.08
    onia
    0.07
    STAR
    0.07
     Pocket
    0.07
     Scha
    0.07
     pocket
    0.07
     Beat
    0.07
    -Star
    0.07
    Activations Density 0.076%

    No Known Activations