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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 90009
    Prev
    Next
    INDEX
    Explanations

    elements related to mathematical sequences and structures

    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
    iris
    -0.09
    abe
    -0.07
    /Grid
    -0.07
     célib
    -0.07
    roscope
    -0.07
    stretch
    -0.07
    ahy
    -0.07
    USTER
    -0.07
     bist
    -0.06
    OutOf
    -0.06
    POSITIVE LOGITS
    lington
    0.06
     Salv
    0.06
     Punch
    0.06
    <tag
    0.06
    emoc
    0.06
    oral
    0.06
    istor
    0.06
     resolutions
    0.06
    (completion
    0.06
     Petty
    0.06
    Activations Density 0.011%

    No Known Activations