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. 95796
    Prev
    Next
    INDEX
    Explanations

    terms related to multifunctionality and versatile applications

    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
    èĸ
    -0.07
    uren
    -0.06
    finity
    -0.06
    605
    -0.06
    odable
    -0.06
    shall
    -0.06
    719
    -0.06
    skyt
    -0.06
    /the
    -0.06
    zia
    -0.06
    POSITIVE LOGITS
    ạnh
    0.07
    Ù쨧ÙĤ
    0.06
    -purpose
    0.06
    yen
    0.06
     Mul
    0.06
    FileType
    0.06
    vore
    0.06
    orsch
    0.06
    resultSet
    0.06
    .undefined
    0.06
    Activations Density 0.003%

    No Known Activations