© 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. 15-LLAMASCOPE-RES-131K
    11. 26804
    Prev
    Next
    INDEX
    Explanations

    terms indicating increasing trends or amounts

    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
    wap
    -0.07
    stral
    -0.07
    aca
    -0.07
    çºĮ
    -0.07
    ournament
    -0.06
    ChangeListener
    -0.06
    utsch
    -0.06
    qus
    -0.06
    kc
    -0.06
    isle
    -0.06
    POSITIVE LOGITS
     increasingly
    0.08
    ÑĬ
    0.07
    .rar
    0.07
    abouts
    0.06
    otine
    0.06
     separation
    0.06
    hev
    0.06
    arov
    0.06
     Siz
    0.06
    .zip
    0.06
    Activations Density 0.028%

    No Known Activations