© 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. 127011
    Prev
    Next
    INDEX
    Explanations

    census data and statistical information

    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
     Das
    -0.06
    olit
    -0.06
    u
    -0.06
    ÑģÑĤÑİ
    -0.05
    еви
    -0.05
    evin
    -0.05
    olith
    -0.05
     Dom
    -0.05
     ff
    -0.05
     frees
    -0.05
    POSITIVE LOGITS
    ãĥ«ãĤ¯
    0.07
    iya
    0.07
     pog
    0.07
    acente
    0.07
    .ColumnHeader
    0.07
    ¬ģ
    0.07
    .library
    0.07
    ynamics
    0.07
    æł¼
    0.07
    .nano
    0.06
    Activations Density 0.001%

    No Known Activations