© 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. 15-LLAMASCOPE-RES-131K
    6. 26894
    Prev
    Next
    INDEX
    Explanations

    URLs and web links

    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
    (___
    -0.07
    erson
    -0.07
    acea
    -0.07
    otle
    -0.06
    лаÑĩ
    -0.06
    å¦ĥ
    -0.06
    drv
    -0.06
    á»ĭch
    -0.06
    .ps
    -0.06
    ynos
    -0.06
    POSITIVE LOGITS
     hog
    0.06
    GenerationStrategy
    0.06
     liability
    0.06
    eed
    0.06
     LIABILITY
    0.06
    /Framework
    0.06
    903
    0.06
    aba
    0.06
    be
    0.05
    PropertyDescriptor
    0.05
    Activations Density 0.002%

    No Known Activations