© 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. 15-LLAMASCOPE-RES-131K
    6. 62170
    Prev
    Next
    INDEX
    Explanations

    references to specific political events or figures

    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
    à¸Ļà¸Ń
    -0.07
    ãĥ³ãĤº
    -0.07
    ÑĤин
    -0.06
     çöz
    -0.06
    avers
    -0.06
    á»įng
    -0.06
     ÅĻÃŃj
    -0.06
    .blogspot
    -0.06
    ippi
    -0.06
    [attr
    -0.06
    POSITIVE LOGITS
    gov
    0.07
    kowski
    0.06
    žel
    0.06
    foot
    0.06
     unprecedented
    0.06
     inclus
    0.06
    LinkId
    0.06
     coron
    0.06
    ownt
    0.06
    uez
    0.06
    Activations Density 0.007%

    No Known Activations