© 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. 90059
    Prev
    Next
    INDEX
    Explanations

    phrases indicating references to specific subjects or entities

    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
    owo
    -0.08
    erty
    -0.08
    aji
    -0.07
    afa
    -0.07
    ово
    -0.07
    apult
    -0.07
    cka
    -0.07
    olib
    -0.07
    ransition
    -0.07
    tolua
    -0.07
    POSITIVE LOGITS
    illis
    0.07
     Tar
    0.06
    MAND
    0.06
     span
    0.06
     context
    0.06
    ritis
    0.06
     Rud
    0.06
     case
    0.06
    ambi
    0.05
     instance
    0.05
    Activations Density 0.018%

    No Known Activations