© 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. 58952
    Prev
    Next
    INDEX
    Explanations

    financial performance indicators and analysis references

    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
    .FontStyle
    -0.07
    .office
    -0.06
    ê·¼
    -0.06
    ãģĭãģĦ
    -0.06
    creasing
    -0.06
    VS
    -0.06
    ura
    -0.06
    ¿ł
    -0.06
    _NONNULL
    -0.06
    .crm
    -0.06
    POSITIVE LOGITS
     mean
    0.07
     Mean
    0.06
    paragus
    0.06
    ÑĢи
    0.06
    reads
    0.06
    Mean
    0.06
    á»ķ
    0.06
    pter
    0.06
     altogether
    0.06
    odzi
    0.05
    Activations Density 0.028%

    No Known Activations