© 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. 28887
    Prev
    Next
    INDEX
    Explanations

    parameters related to configuration settings

    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
    .ov
    -0.08
    agedList
    -0.07
    oval
    -0.07
    entence
    -0.07
    loud
    -0.07
    ãĥ¼ãĥĭ
    -0.07
    .scalablytyped
    -0.07
    ¤í
    -0.07
    AtA
    -0.07
    inke
    -0.07
    POSITIVE LOGITS
     or
    0.08
    æĪĸ
    0.07
     tune
    0.06
     oder
    0.06
    1
    0.06
    æĪĸèĢħ
    0.06
    arl
    0.06
     tun
    0.06
    ãĥªãĥ¼
    0.06
    ovich
    0.06
    Activations Density 0.045%

    No Known Activations