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. 95871
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and structures related to permissions and session management

    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
    uling
    -0.07
    inn
    -0.06
    istributed
    -0.06
    asy
    -0.06
    ayah
    -0.06
    omens
    -0.06
     samen
    -0.06
    å¥Ī
    -0.06
     inn
    -0.06
    entine
    -0.06
    POSITIVE LOGITS
    ##_
    0.07
    roid
    0.06
    .nih
    0.06
    çļĦåľ°
    0.06
    zia
    0.06
    asco
    0.06
    loh
    0.06
    ãĤ¹ãģ®
    0.06
    /Area
    0.06
    andin
    0.06
    Activations Density 0.034%

    No Known Activations