© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 29409
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and operations in a technical context

    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
    aver
    -0.07
     BAD
    -0.06
    quot
    -0.06
     unb
    -0.06
    esium
    -0.06
    amp
    -0.06
    ÑĢаÑĤи
    -0.06
    BAD
    -0.06
    ogan
    -0.06
     PROP
    -0.06
    POSITIVE LOGITS
    quier
    0.07
    ModelProperty
    0.07
    _tF
    0.06
    viÄį
    0.06
    onga
    0.06
    άÏģÏĩ
    0.06
    azÄĥ
    0.06
    =yes
    0.06
    ç½
    0.06
    .SizeF
    0.06
    Activations Density 0.003%

    No Known Activations