Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95787
    Prev
    Next
    INDEX
    Explanations

    terms related to read-only memory and access restrictions

    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
    irth
    -0.09
    ä»¶
    -0.07
    loy
    -0.07
    ixo
    -0.06
    ese
    -0.06
    adr
    -0.06
    fall
    -0.06
     noir
    -0.06
    aha
    -0.06
    .liferay
    -0.06
    POSITIVE LOGITS
    /free
    0.07
    üf
    0.07
    hipster
    0.07
     Cunning
    0.06
    Enumerator
    0.06
    sdale
    0.06
    kah
    0.06
    ::__
    0.06
    illac
    0.06
    rost
    0.06
    Activations Density 0.003%

    No Known Activations