© 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. 17-LLAMASCOPE-RES-131K
    11. 74404
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a topic of discussion

    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
    izable
    -0.08
    ities
    -0.08
    fault
    -0.07
    XF
    -0.07
    eros
    -0.07
    оÑĢоз
    -0.07
    оÑĢо
    -0.06
     dán
    -0.06
    VS
    -0.06
    berg
    -0.06
    POSITIVE LOGITS
    -NLS
    0.09
    /from
    0.08
     طرÙĬÙĤ
    0.08
     how
    0.07
    e
    0.07
    avia
    0.07
    .gdx
    0.07
    -face
    0.07
     the
    0.07
    /to
    0.07
    Activations Density 0.128%

    No Known Activations