Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 126728
    Prev
    Next
    INDEX
    Explanations

    numerical representations and statistical data

    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
    oleans
    -0.07
    bian
    -0.07
    pgsql
    -0.06
    ollah
    -0.06
    ibu
    -0.06
    yg
    -0.06
     @{↵
    -0.06
    Å¡tÄĽ
    -0.06
    äm
    -0.06
    ize
    -0.06
    POSITIVE LOGITS
    ryo
    0.07
    chnitt
    0.06
    831
    0.06
    psc
    0.06
    ë¶Ī
    0.06
    åļ
    0.06
    .RestController
    0.06
     Belle
    0.06
    ORY
    0.06
     CBS
    0.06
    Activations Density 0.001%

    No Known Activations