© 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 EvalsExportsinterp-engineNEWAPI 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. 31149
    Prev
    Next
    INDEX
    Explanations

    references to various types of models and modeling processes

    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
    es
    -0.08
    keit
    -0.08
    ìĦľëĬĶ
    -0.08
    enne
    -0.07
    ا
    -0.07
    falls
    -0.07
    esin
    -0.07
    dar
    -0.07
    ember
    -0.06
    ëĬĶ
    -0.06
    POSITIVE LOGITS
    led
    0.18
    ë§ģ
    0.10
    ocked
    0.10
    UnderTest
    0.08
    ogue
    0.08
    AndView
    0.08
    VERRIDE
    0.08
    .Model
    0.08
    lo
    0.08
    ateral
    0.08
    Activations Density 0.053%

    No Known Activations