© 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. 125438
    Prev
    Next
    INDEX
    Explanations

    references to medical research studies and their applications

    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
    çļĦè¯Ŀ
    -0.07
     punching
    -0.06
    riteln
    -0.06
    един
    -0.06
     ULONG
    -0.06
    aison
    -0.06
    amination
    -0.06
     تط
    -0.06
    547
    -0.06
    legt
    -0.06
    POSITIVE LOGITS
    onis
    0.06
     strSql
    0.06
    ican
    0.06
    iana
    0.06
    utron
    0.06
    orado
    0.06
    ag
    0.06
    ello
    0.06
    quina
    0.06
    ÂĮ
    0.05
    Activations Density 0.000%

    No Known Activations