© 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. 9-LLAMASCOPE-RES-131K
    11. 95549
    Prev
    Next
    INDEX
    Explanations

    titles or headings

    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
    529
    -0.07
    ±Ð¾ÑĤ
    -0.07
    boot
    -0.07
    aret
    -0.07
    adget
    -0.07
    pedo
    -0.07
    ared
    -0.07
    zcze
    -0.07
     Stranger
    -0.07
    urgeon
    -0.07
    POSITIVE LOGITS
    dar
    0.06
     conv
    0.06
    demand
    0.06
     Kil
    0.06
    ilan
    0.06
     demand
    0.06
     pl
    0.06
    èĽĽ
    0.06
     prov
    0.06
    aku
    0.06
    Activations Density 0.001%

    No Known Activations