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. 76610
    Prev
    Next
    INDEX
    Explanations

    references to online content and allegations regarding copyright infringement

    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
    zas
    -0.07
    perial
    -0.06
    itzer
    -0.06
    akis
    -0.06
    ka
    -0.06
     consumption
    -0.06
    anka
    -0.06
    âłĢ
    -0.06
    ftp
    -0.06
    amba
    -0.06
    POSITIVE LOGITS
    upal
    0.08
    afone
    0.07
     posts
    0.06
    ysi
    0.06
    ilder
    0.06
    _THREAD
    0.06
    ãģĵãģ¡ãĤī
    0.06
     fend
    0.06
    ÑıÑĤелÑĮ
    0.06
    .decorate
    0.06
    Activations Density 0.005%

    No Known Activations