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. 96157
    Prev
    Next
    INDEX
    Explanations

    programming syntax and structure

    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
    erg
    -0.07
    ersh
    -0.07
    phinx
    -0.06
    ARP
    -0.06
     Lewis
    -0.06
     Stevenson
    -0.06
    ignon
    -0.06
    ãĤ·ãĥ¥
    -0.06
     Ing
    -0.06
     lut
    -0.06
    POSITIVE LOGITS
    kaç
    0.08
    -fontawesome
    0.07
    à¥Ģà¤Ł
    0.07
     moden
    0.07
     å
    0.07
    _atual
    0.07
    иÑģÑģ
    0.06
    acons
    0.06
    \OptionsResolver
    0.06
    asia
    0.06
    Activations Density 0.000%

    No Known Activations