© 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 EvalsExportsinterp-engineNEWAPI 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. 18012
    Prev
    Next
    INDEX
    Explanations

    references to the number of pages in documents or papers

    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
     quer
    -0.06
    ambi
    -0.06
     ad
    -0.06
    ser
    -0.06
    quer
    -0.06
    less
    -0.05
     coinc
    -0.05
     l
    -0.05
     sc
    -0.05
     "
    -0.05
    POSITIVE LOGITS
    arp
    0.08
    romo
    0.07
    íĻĢ
    0.07
    intColor
    0.07
    -gnu
    0.07
    ushima
    0.07
    аниÑĨ
    0.07
    ãĥ¼ãĥĪ
    0.07
    CREMENT
    0.07
    yntax
    0.07
    Activations Density 0.001%

    No Known Activations