© 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. 57334
    Prev
    Next
    INDEX
    Explanations

    instances of numerical quantities or counts

    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
    .LayoutStyle
    -0.08
    Ïħγ
    -0.08
    activex
    -0.07
     podrob
    -0.07
    ching
    -0.07
    ève
    -0.07
    chers
    -0.07
    avana
    -0.07
    okino
    -0.07
    enders
    -0.07
    POSITIVE LOGITS
    -member
    0.07
     young
    0.07
     brothers
    0.06
     siblings
    0.06
     amigos
    0.06
     mus
    0.06
    æ·
    0.06
     male
    0.05
    tron
    0.05
     guys
    0.05
    Activations Density 0.024%

    No Known Activations