© 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. 27288
    Prev
    Next
    INDEX
    Explanations

    numerical specifications and measurements related to materials and products

    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
    egal
    -0.09
    ADATA
    -0.08
    undler
    -0.07
    OTOR
    -0.07
    erator
    -0.07
    .scalablytyped
    -0.07
    pac
    -0.06
     visceral
    -0.06
    itti
    -0.06
     onBind
    -0.06
    POSITIVE LOGITS
     steel
    0.07
     strength
    0.07
     tens
    0.06
     antis
    0.06
     exposed
    0.06
    ıt
    0.06
     Shed
    0.06
     cod
    0.06
    stal
    0.06
     mild
    0.06
    Activations Density 0.001%

    No Known Activations