© 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. 17-LLAMASCOPE-RES-131K
    11. 3815
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to linguistics and language structure

    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
    raphics
    -0.08
    -syntax
    -0.07
    agini
    -0.07
    اÙģت
    -0.07
    edBy
    -0.07
    _Window
    -0.07
    ToDevice
    -0.07
    AccessType
    -0.07
    /access
    -0.07
    otty
    -0.07
    POSITIVE LOGITS
     Roman
    0.08
     Rome
    0.06
    Roman
    0.06
    onom
    0.06
     stable
    0.06
     representations
    0.06
     spor
    0.06
     Pl
    0.06
     Greg
    0.06
     V
    0.06
    Activations Density 0.001%

    No Known Activations