© 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. 125417
    Prev
    Next
    INDEX
    Explanations

    phrases related to opinions and testimonials

    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
    ãĥ³ãĤ°ãĥ«
    -0.07
    ettel
    -0.07
    arga
    -0.06
    ufac
    -0.06
    itou
    -0.06
    entine
    -0.06
    anko
    -0.06
    dek
    -0.06
     Buffer
    -0.06
    omi
    -0.06
    POSITIVE LOGITS
     feedback
    0.09
     testimonials
    0.09
     testimony
    0.08
     testify
    0.08
     testim
    0.07
     Feedback
    0.07
    edback
    0.07
     testimon
    0.07
    feedback
    0.07
    imonials
    0.07
    Activations Density 0.011%

    No Known Activations