© 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. 103993
    Prev
    Next
    INDEX
    Explanations

    programming terminology 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
    заб
    -0.07
    ongo
    -0.07
    nesc
    -0.07
    NIL
    -0.07
    .Identity
    -0.07
    rve
    -0.07
    ï¼ł
    -0.07
    ONGO
    -0.07
    ivatel
    -0.07
    ManagedObject
    -0.07
    POSITIVE LOGITS
    atica
    0.06
     g
    0.06
    éĥ
    0.06
     global
    0.06
    ucci
    0.06
     rewarding
    0.06
    AAF
    0.06
     action
    0.05
    ovenant
    0.05
     moving
    0.05
    Activations Density 0.005%

    No Known Activations