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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 3492
    Prev
    Next
    INDEX
    Explanations

    terminology related to technological specifications and features

    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
    ixa
    -0.08
    terra
    -0.08
    ãĤ¡
    -0.07
    aroo
    -0.07
    usalem
    -0.07
    ugi
    -0.07
     Conc
    -0.07
    Navigator
    -0.06
     LES
    -0.06
    abee
    -0.06
    POSITIVE LOGITS
    hes
    0.08
     dah
    0.07
     Guil
    0.07
     TOP
    0.07
    otime
    0.07
    eken
    0.06
    åĪĩãĤĬ
    0.06
     Yunan
    0.06
     Evet
    0.06
     Bo
    0.06
    Activations Density 0.021%

    No Known Activations