© 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. 94091
    Prev
    Next
    INDEX
    Explanations

    terms related to downloading or saving images and setting background wallpapers

    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
    yn
    -0.07
    atter
    -0.07
    yp
    -0.06
    isson
    -0.05
    ¹
    -0.05
     Mk
    -0.05
     Gott
    -0.05
    iedo
    -0.05
    vim
    -0.05
    aten
    -0.05
    POSITIVE LOGITS
    BlockSize
    0.07
    ãĥ³ãĥĨãĤ£
    0.07
    hung
    0.07
    fern
    0.07
    .assets
    0.07
    reeNode
    0.06
     pokoj
    0.06
    rous
    0.06
    íķ
    0.06
    ãĥ¼ãĥ©
    0.06
    Activations Density 0.001%

    No Known Activations