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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 5-LLAMASCOPE-RES-131K
    6. 125578
    Prev
    Next
    INDEX
    Explanations

    references to software components and programming environments

    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
     past
    -0.07
    raith
    -0.07
    rant
    -0.06
     mun
    -0.06
    277
    -0.06
     wax
    -0.06
    edar
    -0.06
     Archer
    -0.06
    onga
    -0.06
     Operation
    -0.06
    POSITIVE LOGITS
    رÛĮز
    0.08
    ľ
    0.07
    /Internal
    0.07
     newcom
    0.06
    ARED
    0.06
    ILED
    0.06
    ìĥģìľĦ
    0.06
    ảnh
    0.06
    èĥİ
    0.06
     rencont
    0.06
    Activations Density 0.006%

    No Known Activations