© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 4246
    Prev
    Next
    INDEX
    Explanations

    terms related to construction and architecture

    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
    ien
    -0.08
    isme
    -0.07
    adge
    -0.07
    ave
    -0.07
    hots
    -0.06
    šov
    -0.06
    969
    -0.06
    688
    -0.06
    è²
    -0.06
    347
    -0.06
    POSITIVE LOGITS
    oki
    0.08
    yl
    0.07
    ycz
    0.06
    yle
    0.06
    yn
    0.06
    ym
    0.06
     Pic
    0.06
    ypi
    0.06
    ãģļ
    0.06
    ãĥ³ãĥ
    0.06
    Activations Density 0.027%

    No Known Activations