© 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. 15-LLAMASCOPE-RES-131K
    11. 632
    Prev
    Next
    INDEX
    Explanations

    punctuation and special characters related to formatting or syntax

    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
    erson
    -0.06
     Georg
    -0.06
    Ãłu
    -0.06
    åºĦ
    -0.06
     thus
    -0.05
     al
    -0.05
    Extern
    -0.05
    ult
    -0.05
    /wait
    -0.05
    orre
    -0.05
    POSITIVE LOGITS
    ãģĵãģ¡ãĤī
    0.07
     lorem
    0.07
     addCriterion
    0.07
    èĩ
    0.07
    -REAL
    0.07
    ewater
    0.07
    ulla
    0.07
     enthusi
    0.07
    ARB
    0.07
    uffy
    0.06
    Activations Density 0.006%

    No Known Activations