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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 58029
    Prev
    Next
    INDEX
    Explanations

    references to personal relationships and gift suggestions

    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
    oodle
    -0.07
     ç©
    -0.06
    indow
    -0.06
    omba
    -0.06
    Forgot
    -0.06
    enstein
    -0.06
    ãĥĥãĥģ
    -0.06
    ince
    -0.06
    neys
    -0.06
    ither
    -0.06
    POSITIVE LOGITS
    buz
    0.06
    638
    0.06
    šk
    0.06
     kinds
    0.06
     resend
    0.06
    .EventArgs
    0.06
    ï¼Į
    0.06
    )size
    0.06
    ška
    0.06
    hq
    0.06
    Activations Density 0.011%

    No Known Activations