© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 77941
    Prev
    Next
    INDEX
    Explanations

    information related to recordings and discussions involving a particular group or subject matter

    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
    anut
    -0.07
    ullen
    -0.07
    еÑĢп
    -0.07
    anuts
    -0.07
    jeme
    -0.07
    ytt
    -0.07
    èn
    -0.07
     écrit
    -0.07
     åĨ
    -0.07
    ewriter
    -0.07
    POSITIVE LOGITS
     recording
    0.10
     recordings
    0.10
     audio
    0.09
     recorded
    0.09
    -record
    0.08
     conversations
    0.08
     conversation
    0.08
     Recording
    0.07
     recorder
    0.07
    audio
    0.07
    Activations Density 0.006%

    No Known Activations