Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96153
    Prev
    Next
    INDEX
    Explanations

    references to testing assertions in programming code

    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
    akis
    -0.07
     prere
    -0.06
     sou
    -0.06
    極
    -0.06
    che
    -0.06
     Hass
    -0.05
    ieux
    -0.05
     Sou
    -0.05
     whose
    -0.05
     SE
    -0.05
    POSITIVE LOGITS
    veis
    0.08
    ograd
    0.08
    belt
    0.07
    erton
    0.07
    htar
    0.07
    kker
    0.07
    eÄį
    0.07
    bsites
    0.07
    /umd
    0.07
    @js
    0.07
    Activations Density 0.000%

    No Known Activations