© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 72647
    Prev
    Next
    INDEX
    Explanations

    references to downloadable content, indicating various media resources

    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
    ment
    -0.06
     Vict
    -0.06
    anding
    -0.05
    Id
    -0.05
    ↵
    -0.05
    ,↵
    -0.05
    ,
    -0.05
     Nation
    -0.05
     wiki
    -0.05
    âĢ¦↵
    -0.05
    POSITIVE LOGITS
    .wav
    0.09
    odcast
    0.09
     podcast
    0.09
    pod
    0.08
     Podcast
    0.08
    .Pod
    0.08
    AUDIO
    0.08
    .ogg
    0.08
     anale
    0.08
    _pod
    0.08
    Activations Density 0.003%

    No Known Activations