© 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. 77505
    Prev
    Next
    INDEX
    Explanations

    commands and actions related to file and directory manipulation in a technical context

    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
    iaux
    -0.08
    aub
    -0.08
    stre
    -0.08
     огÑĢа
    -0.08
    rien
    -0.08
    .onView
    -0.08
    ECT
    -0.07
    ]âĢı
    -0.07
    LBL
    -0.07
    afb
    -0.07
    POSITIVE LOGITS
    311
    0.06
    ÑĩиÑģ
    0.05
     ins
    0.05
     C
    0.05
     E
    0.05
    ans
    0.05
     Ab
    0.05
     sub
    0.05
     L
    0.05
     str
    0.05
    Activations Density 0.002%

    No Known Activations