© 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. 15-LLAMASCOPE-RES-131K
    11. 89924
    Prev
    Next
    INDEX
    Explanations

    keywords related to scientific measurements and configurations

    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
     ref
    -0.07
     ad
    -0.06
     Bra
    -0.06
    pas
    -0.06
    zz
    -0.06
     masa
    -0.06
     others
    -0.05
    hra
    -0.05
     slick
    -0.05
    hr
    -0.05
    POSITIVE LOGITS
    WithURL
    0.08
    mtree
    0.08
    EXPECT
    0.08
    vap
    0.08
    rowsable
    0.07
    ÃŃg
    0.07
    #ac
    0.07
    Exposed
    0.07
    abinet
    0.07
    ureau
    0.07
    Activations Density 0.071%

    No Known Activations