© 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. 78740
    Prev
    Next
    INDEX
    Explanations

    terms related to constraints and conditions in a programming or algorithmic 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
    ventions
    -0.07
    325
    -0.07
     talent
    -0.06
    abus
    -0.06
    236
    -0.06
    376
    -0.06
    764
    -0.06
    otal
    -0.06
    326
    -0.06
    Sec
    -0.06
    POSITIVE LOGITS
     EITHER
    0.08
     either
    0.07
    Äĥr
    0.07
     Jad
    0.07
    _COMPILE
    0.06
    *)((
    0.06
     Cald
    0.06
    tas
    0.06
    leaf
    0.06
     leaf
    0.06
    Activations Density 0.010%

    No Known Activations