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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 96128
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions

    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
    pen
    -0.06
    asaki
    -0.06
    oes
    -0.06
     as
    -0.05
     sooner
    -0.05
    expo
    -0.05
     ashes
    -0.05
     versus
    -0.05
    onna
    -0.05
    ores
    -0.05
    POSITIVE LOGITS
    odos
    0.08
     Annotations
    0.07
    ãĤ¦ãĥĪ
    0.07
    .localization
    0.07
    _tF
    0.07
    _SRV
    0.07
    ationToken
    0.07
    .Localization
    0.07
    ãĥ«ãĥī
    0.07
    TAG
    0.07
    Activations Density 0.003%

    No Known Activations