© 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. 17-LLAMASCOPE-RES-131K
    11. 40479
    Prev
    Next
    INDEX
    Explanations

    references to figures within the text

    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
    iw
    -0.07
    .gdx
    -0.07
    öm
    -0.07
    oise
    -0.07
    polator
    -0.07
    izedName
    -0.07
    bilt
    -0.06
    edException
    -0.06
    ozy
    -0.06
    ationale
    -0.06
    POSITIVE LOGITS
    ures
    0.10
    uration
    0.08
    keit
    0.08
    soever
    0.07
    URES
    0.07
    uring
    0.07
    son
    0.07
    oya
    0.07
    dem
    0.07
    asaki
    0.07
    Activations Density 0.027%

    No Known Activations