© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 61895
    Prev
    Next
    INDEX
    Explanations

    references to programming structures and modules

    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
    lien
    -0.07
    λικά
    -0.07
     unilateral
    -0.06
    oulos
    -0.06
    wal
    -0.06
     Alexandre
    -0.06
    ë§¥
    -0.06
    ÙĪÛĮÙĦ
    -0.06
    ither
    -0.06
    apur
    -0.06
    POSITIVE LOGITS
    enance
    0.08
    /*/
    0.07
    lund
    0.07
     Booker
    0.06
     implicitly
    0.06
    airy
    0.06
    iy
    0.06
    ij¸
    0.06
    072
    0.06
    CESS
    0.06
    Activations Density 0.008%

    No Known Activations