© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 71066
    Prev
    Next
    INDEX
    Explanations

    references to academic details and structures in philosophical literature

    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
     Kapoor
    -0.07
    onet
    -0.07
    ãĥ³ãĥĩ
    -0.07
     others
    -0.07
    alse
    -0.06
    rops
    -0.06
    kte
    -0.06
    ooke
    -0.06
    ktor
    -0.06
    kova
    -0.06
    POSITIVE LOGITS
    Challenge
    0.06
     Kaf
    0.06
     Challenge
    0.06
     ãĢ
    0.06
    ohl
    0.06
    challenge
    0.06
    éłĵ
    0.06
    @student
    0.06
     Alman
    0.06
    άÏĤ
    0.06
    Activations Density 0.009%

    No Known Activations