© 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. 70956
    Prev
    Next
    INDEX
    Explanations

    discussions about remote work and its implications

    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
    alim
    -0.09
    inke
    -0.08
    thouse
    -0.07
     Karlov
    -0.07
    ynet
    -0.07
    MemoryWarning
    -0.07
    ifest
    -0.07
    getti
    -0.07
    assed
    -0.07
    ilden
    -0.07
    POSITIVE LOGITS
     remote
    0.13
     Remote
    0.11
    Remote
    0.10
    remote
    0.10
    .Remote
    0.10
     tele
    0.09
    _remote
    0.09
     remotely
    0.09
    .remote
    0.09
    (remote
    0.09
    Activations Density 0.047%

    No Known Activations