© 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. 27256
    Prev
    Next
    INDEX
    Explanations

    concepts related to mining operations and methods

    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
    stadt
    -0.08
    /spec
    -0.07
    hev
    -0.07
     Bid
    -0.06
     serviceProvider
    -0.06
    ristol
    -0.06
    753
    -0.06
    _nth
    -0.06
     dod
    -0.06
    EDIATE
    -0.06
    POSITIVE LOGITS
    дал
    0.07
    onden
    0.07
    ogn
    0.07
    icut
    0.06
    .opens
    0.06
    pad
    0.06
     mand
    0.06
     gravity
    0.06
     blend
    0.06
    jmp
    0.06
    Activations Density 0.022%

    No Known Activations