© 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. 22-LLAMASCOPE-RES-131K
    11. 4268
    Prev
    Next
    INDEX
    Explanations

    references to HTML documents or file types

    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
     fo
    -0.07
    ouns
    -0.07
    ersions
    -0.06
    emm
    -0.06
    æ½
    -0.06
    rapper
    -0.06
    ãģĸ
    -0.06
    ingly
    -0.06
    line
    -0.06
    umin
    -0.05
    POSITIVE LOGITS
     stddev
    0.07
    amd
    0.06
    ataire
    0.06
    upa
    0.06
    -alist
    0.06
    ulaire
    0.06
     Thi
    0.06
    ECT
    0.06
    WebHost
    0.06
     onload
    0.06
    Activations Density 0.001%

    No Known Activations