© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 56038
    Prev
    Next
    INDEX
    Explanations

    conditional statements typically used in programming logic

    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
    phinx
    -0.07
     Pill
    -0.07
    βάλ
    -0.06
    ë°ĶìĿ´
    -0.06
    ë°±
    -0.06
    opoulos
    -0.06
    å½
    -0.06
    _INCREF
    -0.06
    OLON
    -0.06
    rud
    -0.06
    POSITIVE LOGITS
     super
    0.07
    akes
    0.06
    aket
    0.06
     mach
    0.06
    haus
    0.06
     mascul
    0.06
     Mach
    0.06
    aska
    0.06
     already
    0.06
     tiếng
    0.06
    Activations Density 0.039%

    No Known Activations