© 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. 15-LLAMASCOPE-RES-131K
    11. 62377
    Prev
    Next
    INDEX
    Explanations

    information related to research institutions and collaborations

    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
     Ø¢Ùħ
    -0.08
    ouz
    -0.08
    isel
    -0.07
    Assignable
    -0.07
    iggs
    -0.07
    اج
    -0.07
    pref
    -0.06
    /browse
    -0.06
    Race
    -0.06
     race
    -0.06
    POSITIVE LOGITS
     elsewhere
    0.09
     cot
    0.06
     Element
    0.06
     partners
    0.06
    หลวà¸ĩ
    0.06
    argins
    0.06
    ahren
    0.06
    AIT
    0.06
    ifen
    0.05
    eniable
    0.05
    Activations Density 0.031%

    No Known Activations