© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 93858
    Prev
    Next
    INDEX
    Explanations

    success stories and achievements of individuals in community programs

    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
    FML
    -0.08
    locker
    -0.07
    åĢ
    -0.07
    IONS
    -0.07
    :CGRect
    -0.07
     rfl
    -0.07
    Bru
    -0.07
    fad
    -0.07
    ä»°
    -0.06
    IOUS
    -0.06
    POSITIVE LOGITS
     successfully
    0.08
     eventual
    0.08
     subsequently
    0.08
     eventually
    0.08
     now
    0.07
     subsequent
    0.07
     successful
    0.07
     recently
    0.07
     diligence
    0.07
    successfully
    0.06
    Activations Density 0.029%

    No Known Activations