© 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. 57521
    Prev
    Next
    INDEX
    Explanations

    quantitative measures and comparisons in data 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
    èIJ½
    -0.06
    ogue
    -0.06
     بÙĨÛĮ
    -0.06
    rof
    -0.06
    éĩı
    -0.06
    fell
    -0.06
    ylan
    -0.06
     å¸ĥ
    -0.06
    oin
    -0.06
    errick
    -0.05
    POSITIVE LOGITS
     scale
    0.12
     relative
    0.12
     Relative
    0.11
    relative
    0.10
     SCALE
    0.10
     ratio
    0.10
     Scale
    0.10
     ratios
    0.10
    -relative
    0.09
    :relative
    0.09
    Activations Density 0.087%

    No Known Activations