© 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. 28558
    Prev
    Next
    INDEX
    Explanations

    terms that denote a high level of experience or qualifications

    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
    geist
    -0.08
    gli
    -0.08
    gons
    -0.07
    istik
    -0.06
    ou
    -0.06
    laus
    -0.06
    ognitive
    -0.06
    /blue
    -0.06
    enti
    -0.06
    esian
    -0.06
    POSITIVE LOGITS
    ness
    0.09
    ines
    0.08
     enough
    0.08
    urance
    0.07
    /lic
    0.07
    rys
    0.07
     Enough
    0.07
    edom
    0.06
    imedia
    0.06
    ernal
    0.06
    Activations Density 0.005%

    No Known Activations