© 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. 86135
    Prev
    Next
    INDEX
    Explanations

    system components and configurations within technical descriptions

    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
    åIJİçļĦ
    -0.08
    acos
    -0.08
    udio
    -0.07
    longleftrightarrow
    -0.07
    sembly
    -0.07
    654
    -0.07
    childs
    -0.07
    ãĤŃãĥ¥
    -0.07
    æķĪæŀľ
    -0.07
    è¹
    -0.07
    POSITIVE LOGITS
     two
    0.07
    lah
    0.07
     normalized
    0.06
    :
    0.06
     a
    0.06
    ony
    0.06
    两个
    0.06
    resa
    0.06
    aan
    0.05
     A
    0.05
    Activations Density 0.033%

    No Known Activations