© 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. 106868
    Prev
    Next
    INDEX
    Explanations

    phrases indicating past actions or 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
    undi
    -0.06
     TORT
    -0.06
    bers
    -0.06
    GC
    -0.06
    ayne
    -0.06
    iversite
    -0.05
    Ïįν
    -0.05
    radu
    -0.05
    cott
    -0.05
    ãĥĥãĤ«ãĥ¼
    -0.05
    POSITIVE LOGITS
    ear
    0.09
    ont
    0.08
    artz
    0.07
    orean
    0.07
    esium
    0.07
     earlier
    0.07
     previously
    0.07
    egen
    0.07
     سابÙĤ
    0.07
    YNAM
    0.07
    Activations Density 0.022%

    No Known Activations