© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 118574
    Prev
    Next
    INDEX
    Explanations

    numerical data related to technology and communication 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
    ết
    -0.08
    ndo
    -0.08
    ernals
    -0.07
    aleb
    -0.07
    oute
    -0.07
    öst
    -0.07
    ãĥ³ãĥī
    -0.07
    igraph
    -0.07
    onte
    -0.07
    MOTE
    -0.07
    POSITIVE LOGITS
    illo
    0.07
    adder
    0.07
    anning
    0.07
     Elm
    0.06
     vis
    0.06
     Carr
    0.06
    uss
    0.06
     Willi
    0.06
     Jenna
    0.06
     Ella
    0.06
    Activations Density 0.051%

    No Known Activations