© 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. 17-LLAMASCOPE-RES-131K
    11. 87683
    Prev
    Next
    INDEX
    Explanations

    references to copyright and related legal terminology

    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
    iegel
    -0.07
    legg
    -0.06
    okin
    -0.06
    ape
    -0.06
    ech
    -0.06
    ãģ£ãģį
    -0.06
    eld
    -0.06
    ells
    -0.06
    owers
    -0.06
    352
    -0.06
    POSITIVE LOGITS
    lv
    0.06
    leo
    0.06
    onz
    0.06
    /LICENSE
    0.06
    hta
    0.06
    XXXX
    0.06
    esan
    0.06
     toes
    0.06
    icht
    0.06
     raz
    0.06
    Activations Density 0.002%

    No Known Activations