© 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. 105984
    Prev
    Next
    INDEX
    Explanations

    references to different levels or scales of analysis

    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
    subcategory
    -0.08
    richt
    -0.07
    unct
    -0.07
    ipay
    -0.06
    _ALLOW
    -0.06
    å¼ı
    -0.06
    697
    -0.06
    subclass
    -0.06
    owan
    -0.06
    rollo
    -0.06
    POSITIVE LOGITS
     macros
    0.09
     scales
    0.09
     smaller
    0.08
     scale
    0.08
    -scale
    0.08
     Microsystems
    0.08
     micro
    0.08
    scale
    0.08
     zoom
    0.08
    Scale
    0.07
    Activations Density 0.043%

    No Known Activations