© 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. 103893
    Prev
    Next
    INDEX
    Explanations

    concepts related to inventory management in gaming

    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
     scre
    -0.07
     VID
    -0.06
     glare
    -0.06
    397
    -0.06
    erif
    -0.06
     Stadium
    -0.06
    rena
    -0.06
     å°
    -0.06
    ifo
    -0.06
     stiffness
    -0.06
    POSITIVE LOGITS
     Obr
    0.07
     Nep
    0.06
    winter
    0.06
     nep
    0.06
    bbe
    0.06
    çħĻ
    0.06
    _alias
    0.06
    ÏĦÏģι
    0.06
    çĪ½
    0.06
    ROUND
    0.06
    Activations Density 0.007%

    No Known Activations