© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 76208
    Prev
    Next
    INDEX
    Explanations

    quantitative measurements and geographical or statistical data

    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
    eyse
    -0.07
    loth
    -0.07
    .MixedReality
    -0.07
    ãĥ£
    -0.07
    FIELD
    -0.07
    antha
    -0.07
    ÙĴت
    -0.07
    OfSize
    -0.06
    onda
    -0.06
    panion
    -0.06
    POSITIVE LOGITS
    人åı£
    0.07
     population
    0.07
    _shapes
    0.06
    lis
    0.06
     bob
    0.06
    APA
    0.06
    lin
    0.06
     herd
    0.06
    shape
    0.06
    Population
    0.06
    Activations Density 0.006%

    No Known Activations