© 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. 78759
    Prev
    Next
    INDEX
    Explanations

    references to time and historical events

    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
    ObjectContext
    -0.07
    rut
    -0.07
    ãģ¾ãģ¾
    -0.07
    estatus
    -0.07
    .quick
    -0.07
     Haut
    -0.06
     ((__
    -0.06
    adla
    -0.06
    ãĥ¼ãĥĭ
    -0.06
    atif
    -0.06
    POSITIVE LOGITS
    æīį
    0.20
     only
    0.13
     finally
    0.13
    æīįèĥ½
    0.13
     THEN
    0.13
     later
    0.12
     Only
    0.12
    Only
    0.11
    only
    0.11
     seulement
    0.11
    Activations Density 0.120%

    No Known Activations