© 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. 40217
    Prev
    Next
    INDEX
    Explanations

    mathematical terminology related to distributions and statistical models

    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
    eling
    -0.07
    ouz
    -0.07
    ůst
    -0.06
    åłĤ
    -0.06
     Appe
    -0.06
     Feast
    -0.06
    561
    -0.06
     Abb
    -0.06
    inator
    -0.06
    prediction
    -0.05
    POSITIVE LOGITS
     distribution
    0.14
     distributions
    0.13
     Distribution
    0.12
    distribution
    0.12
    Distribution
    0.10
     distrib
    0.10
     DISTRIBUT
    0.10
    åĪĨå¸ĥ
    0.09
    _distribution
    0.09
     weighting
    0.09
    Activations Density 0.212%

    No Known Activations