© 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. 106005
    Prev
    Next
    INDEX
    Explanations

    expressions of uncertainty or variation in quantity

    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
    velopment
    -0.07
     nackte
    -0.07
    ategy
    -0.07
    ién
    -0.07
    omik
    -0.06
    alborg
    -0.06
    anzi
    -0.06
    iano
    -0.06
    ž
    -0.06
    rompt
    -0.06
    POSITIVE LOGITS
     cases
    0.12
     situations
    0.10
     case
    0.09
     circumstances
    0.09
     occasions
    0.08
     instances
    0.08
     casos
    0.08
    cases
    0.08
     Cases
    0.07
     caso
    0.07
    Activations Density 0.020%

    No Known Activations