© 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. 87239
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the concept of "multiplicity" or "multiple instances."

    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
    .scalablytyped
    -0.10
    ÑĢап
    -0.08
    orget
    -0.08
    berger
    -0.07
     ActionType
    -0.06
     ấy
    -0.06
    oss
    -0.06
    ÃŃnÄĽ
    -0.06
    ائب
    -0.06
    entes
    -0.06
    POSITIVE LOGITS
     simultaneous
    0.08
     sclerosis
    0.07
     equally
    0.07
    acha
    0.07
     simultaneously
    0.07
    ignKey
    0.06
    arch
    0.06
    azen
    0.06
     grav
    0.06
     parallel
    0.06
    Activations Density 0.042%

    No Known Activations