© 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. 15-LLAMASCOPE-RES-131K
    11. 88637
    Prev
    Next
    INDEX
    Explanations

    references to files and file management systems

    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
    land
    -0.08
    ran
    -0.07
    naire
    -0.07
    ãģĬãĤĬ
    -0.07
    ry
    -0.07
    ally
    -0.07
    all
    -0.07
    ÑĢан
    -0.06
    alla
    -0.06
    lace
    -0.06
    POSITIVE LOGITS
    ëŁ
    0.11
    :///
    0.10
    itoris
    0.10
    å¤
    0.09
    -bodied
    0.08
    owner
    0.08
    aments
    0.08
    owners
    0.08
    entlich
    0.08
    ateria
    0.07
    Activations Density 0.034%

    No Known Activations