© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 89850
    Prev
    Next
    INDEX
    Explanations

    numerical identifiers and addresses

    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
    रल
    -0.07
     Certif
    -0.07
    artz
    -0.07
    vice
    -0.07
    оÑģÑĤаÑĤ
    -0.07
    adt
    -0.07
    edl
    -0.07
    qm
    -0.06
     vice
    -0.06
    yleft
    -0.06
    POSITIVE LOGITS
    808
    0.06
    lessly
    0.06
    çµ
    0.06
    hangi
    0.06
    adero
    0.06
    rupt
    0.06
    less
    0.06
    MEA
    0.06
    pret
    0.06
    pid
    0.06
    Activations Density 0.001%

    No Known Activations