© 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. 95566
    Prev
    Next
    INDEX
    Explanations

    references to legal articles and codes

    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
    ansen
    -0.09
    iec
    -0.07
    ammer
    -0.07
    hausen
    -0.06
    uristic
    -0.06
    elite
    -0.06
     relief
    -0.06
     кÑĢаÑģ
    -0.06
    o
    -0.06
     Fuse
    -0.06
    POSITIVE LOGITS
    azor
    0.07
    วล
    0.06
    ãĥĨãĤ£
    0.06
     è¶
    0.06
    ома
    0.06
    tej
    0.06
    ftime
    0.06
     Miner
    0.06
    tracts
    0.06
     Medina
    0.06
    Activations Density 0.008%

    No Known Activations