Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 3489
    Prev
    Next
    INDEX
    Explanations

    references to monitoring and oversight in various contexts

    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
    _defs
    -0.07
    foreground
    -0.06
    коÑĤ
    -0.06
    Occurred
    -0.06
    oken
    -0.06
    Measurement
    -0.06
    yi
    -0.06
    omain
    -0.06
    OKEN
    -0.06
    _viewer
    -0.06
    POSITIVE LOGITS
     progress
    0.12
     closely
    0.10
    progress
    0.09
    -progress
    0.08
     Progress
    0.08
     activity
    0.08
     whether
    0.07
     performance
    0.07
    _progress
    0.07
     monitors
    0.07
    Activations Density 0.015%

    No Known Activations