© 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. 119983
    Prev
    Next
    INDEX
    Explanations

    titles or significant phrases typically found in literary or artistic contexts

    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
    rig
    -0.07
    :
    -0.06
    vala
    -0.06
    im
    -0.06
    le
    -0.06
    inn
    -0.06
     //
    -0.06
    rick
    -0.06
    ÑĪ
    -0.05
    icky
    -0.05
    POSITIVE LOGITS
    /Gate
    0.08
     Primer
    0.08
     unto
    0.08
    -tm
    0.08
     primer
    0.08
    outu
    0.07
    Sortable
    0.07
    éĨ´
    0.07
     tale
    0.07
     Latter
    0.07
    Activations Density 0.014%

    No Known Activations