© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 119609
    Prev
    Next
    INDEX
    Explanations

    binary choices or dichotomous thinking

    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
    uzzi
    -0.08
    abel
    -0.07
    .sam
    -0.07
    ugg
    -0.07
    952
    -0.06
    707
    -0.06
    ÃŃvel
    -0.06
     ear
    -0.06
    andan
    -0.06
    ابع
    -0.06
    POSITIVE LOGITS
     either
    0.10
    -binary
    0.10
     binary
    0.10
     Either
    0.09
     Binary
    0.09
    binary
    0.09
    Either
    0.08
     Or
    0.08
     dich
    0.08
     EITHER
    0.08
    Activations Density 0.018%

    No Known Activations