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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 71748
    Prev
    Next
    INDEX
    Explanations

    phrases indicating availability or accessibility

    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
    odash
    -0.08
    ombres
    -0.08
    TREE
    -0.08
    ór
    -0.07
    ucher
    -0.07
    èn
    -0.07
    ODEV
    -0.07
    regor
    -0.07
    ève
    -0.07
    kos
    -0.07
    POSITIVE LOGITS
     to
    0.09
     for
    0.07
    ulp
    0.06
    877
    0.06
     sacr
    0.06
     whom
    0.06
    asty
    0.06
    ooke
    0.06
     during
    0.05
     Äijá»ĥ
    0.05
    Activations Density 0.007%

    No Known Activations