Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96147
    Prev
    Next
    INDEX
    Explanations

    symbols and notations related to quantum mechanics or particle physics

    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
     Finch
    -0.06
    eger
    -0.06
    argar
    -0.06
    tract
    -0.06
    amide
    -0.06
    logan
    -0.06
    sth
    -0.06
    outer
    -0.06
    enta
    -0.06
    embro
    -0.06
    POSITIVE LOGITS
    .gdx
    0.07
     HOLDERS
    0.07
    ارات
    0.07
    .synthetic
    0.07
    udd
    0.07
    ROLL
    0.07
    缸
    0.07
    ãĥ©ãĥ³ãĤ¹
    0.07
    ycop
    0.07
    /Dk
    0.07
    Activations Density 0.011%

    No Known Activations