© 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. 29592
    Prev
    Next
    INDEX
    Explanations

    statistical data related to basketball player performance

    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
    rosso
    -0.08
    uae
    -0.08
    ichel
    -0.08
    วà¸ĩ
    -0.07
     Petty
    -0.07
    mazon
    -0.07
    quential
    -0.07
    vida
    -0.07
    ButtonItem
    -0.07
    ervo
    -0.07
    POSITIVE LOGITS
    oose
    0.06
    alien
    0.05
     ana
    0.05
     d
    0.05
     jack
    0.05
     Tear
    0.05
     mineral
    0.05
     je
    0.05
    inci
    0.05
     cy
    0.05
    Activations Density 0.011%

    No Known Activations