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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 82558
    Prev
    Next
    INDEX
    Explanations

    financial metrics and quantities related to mining activities

    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
    ulan
    -0.07
    Inspectable
    -0.07
    uild
    -0.07
    undy
    -0.07
    NF
    -0.07
    ãĥ¼ãĥ
    -0.07
    LOUD
    -0.07
    ilan
    -0.06
    lovak
    -0.06
    ableViewController
    -0.06
    POSITIVE LOGITS
    oure
    0.07
    896
    0.06
    uter
    0.06
    elic
    0.06
     medium
    0.06
    anio
    0.06
     Carmen
    0.06
     Mint
    0.06
    rar
    0.06
    997
    0.06
    Activations Density 0.001%

    No Known Activations