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. 83017
    Prev
    Next
    INDEX
    Explanations

    numerical data or statistical information

    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
    vfs
    -0.08
    ůst
    -0.08
    کارÛĮ
    -0.08
    #ad
    -0.07
    vÄĽt
    -0.07
    ruž
    -0.07
    #ac
    -0.07
    stdbool
    -0.07
    à¥Ģस
    -0.07
    çĶ
    -0.07
    POSITIVE LOGITS
    ovich
    0.06
    /to
    0.06
    yw
    0.06
     Nik
    0.06
    osta
    0.05
    ACITY
    0.05
    usk
    0.05
    adb
    0.05
    rim
    0.05
    ovic
    0.05
    Activations Density 0.001%

    No Known Activations