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. 5-LLAMASCOPE-RES-131K
    6. 126249
    Prev
    Next
    INDEX
    Explanations

    occurrences of verbs related to investigation or review processes

    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
     itself
    -0.07
     themselves
    -0.06
    paque
    -0.06
    ombat
    -0.06
    ild
    -0.06
    age
    -0.06
    tha
    -0.05
    .Forms
    -0.05
    ilden
    -0.05
    ép
    -0.05
    POSITIVE LOGITS
    ANJI
    0.08
    _TUN
    0.07
    Ģ
    0.07
    anto
    0.07
    AccessorType
    0.07
    794
    0.07
    mdl
    0.07
    æĮ¯
    0.07
    .jquery
    0.07
    simp
    0.07
    Activations Density 0.017%

    No Known Activations