© 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. 15-LLAMASCOPE-RES-131K
    6. 90834
    Prev
    Next
    INDEX
    Explanations

    numerical values and associated formatting

    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
    orgia
    -0.07
    maid
    -0.07
    minate
    -0.07
    esson
    -0.07
    w
    -0.06
    333
    -0.06
    pace
    -0.06
    _
    -0.06
    سÛĮ
    -0.06
    jem
    -0.06
    POSITIVE LOGITS
     IDD
    0.08
    ÑģоÑĤ
    0.07
    _dispatch
    0.07
    Leap
    0.07
    Handled
    0.07
    \Mapping
    0.07
    .Dial
    0.07
    olini
    0.07
     Dich
    0.07
     Pra
    0.07
    Activations Density 0.000%

    No Known Activations