© 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. 17-LLAMASCOPE-RES-131K
    6. 105677
    Prev
    Next
    INDEX
    Explanations

    mathematical functions and concepts

    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
     saja
    -0.07
    d
    -0.06
    Writable
    -0.05
    under
    -0.05
     proximity
    -0.05
    mpp
    -0.05
     laure
    -0.05
     Fa
    -0.05
    ायत
    -0.05
     Mar
    -0.05
    POSITIVE LOGITS
    /Instruction
    0.08
    reich
    0.07
     cái
    0.07
    lob
    0.07
    yses
    0.07
    (æľ¨
    0.07
    /course
    0.07
     Angiospermae
    0.07
    çi
    0.07
    ions
    0.07
    Activations Density 0.036%

    No Known Activations