© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 127349
    Prev
    Next
    INDEX
    Explanations

    accounts of military actions and events

    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
    burgh
    -0.07
     Vig
    -0.07
     guarded
    -0.06
    iesz
    -0.06
    burg
    -0.06
    __,__
    -0.06
     vigil
    -0.06
     Brut
    -0.06
     Kub
    -0.06
     burg
    -0.06
    POSITIVE LOGITS
     Bren
    0.07
    ocos
    0.07
    redi
    0.06
    ahlen
    0.06
    éo
    0.06
     mirac
    0.06
    áÄį
    0.06
     cyclic
    0.06
    angers
    0.06
     Concent
    0.06
    Activations Density 0.074%

    No Known Activations