© 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. 82896
    Prev
    Next
    INDEX
    Explanations

    elements related to data analysis in research studies

    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
    ccount
    -0.07
    uben
    -0.06
    æŁ±
    -0.06
    chner
    -0.06
    ingu
    -0.06
    ót
    -0.06
    ouz
    -0.06
    relude
    -0.06
     íķĺëĤĺ
    -0.06
     Ùħب
    -0.06
    POSITIVE LOGITS
     population
    0.12
     populations
    0.11
     sample
    0.10
     samples
    0.10
    population
    0.10
    sample
    0.09
     Population
    0.09
     모ì§ij
    0.08
    Population
    0.08
    samples
    0.08
    Activations Density 0.026%

    No Known Activations