© 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. 17-LLAMASCOPE-RES-131K
    6. 128620
    Prev
    Next
    INDEX
    Explanations

    expressions of personal feelings and plans

    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
    AGIC
    -0.06
    roadcast
    -0.06
    ãģĭãģij
    -0.06
     Voll
    -0.06
    Ĥ¹
    -0.06
    erspective
    -0.06
     Hole
    -0.06
    pecific
    -0.06
     rumor
    -0.06
     <=>
    -0.06
    POSITIVE LOGITS
    ahn
    0.08
    Lastly
    0.06
    /{{
    0.06
     ÃĤu
    0.06
    uen
    0.06
     ITE
    0.06
    ock
    0.06
    ofil
    0.06
    uzzi
    0.06
    artz
    0.06
    Activations Density 0.071%

    No Known Activations