© 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. 57541
    Prev
    Next
    INDEX
    Explanations

    information about cannabinoids and their effects

    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
     permanent
    -0.06
     stop
    -0.06
     requirements
    -0.06
    alar
    -0.06
    ā
    -0.06
    çݯ
    -0.06
    fork
    -0.06
    ThreadId
    -0.06
     Requirements
    -0.05
    éļIJ
    -0.05
    POSITIVE LOGITS
    ahlen
    0.07
     è¦
    0.07
    assis
    0.06
    pectrum
    0.06
    akens
    0.06
    (mi
    0.06
     extracted
    0.06
    OfClass
    0.06
    iami
    0.06
    imir
    0.06
    Activations Density 0.002%

    No Known Activations