© 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. 15-LLAMASCOPE-RES-131K
    11. 88040
    Prev
    Next
    INDEX
    Explanations

    references to photography

    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
    ź
    -0.07
    PerPage
    -0.07
    785
    -0.07
     åĬ
    -0.06
    ventory
    -0.06
    ecko
    -0.06
     Kens
    -0.06
     polic
    -0.06
    /MPL
    -0.06
    holm
    -0.06
    POSITIVE LOGITS
    ISO
    0.08
    lein
    0.07
    esz
    0.07
     captured
    0.07
    _HDR
    0.07
     ISO
    0.07
    alis
    0.06
    ược
    0.06
     Pods
    0.06
    noinspection
    0.06
    Activations Density 0.041%

    No Known Activations