© 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. 125012
    Prev
    Next
    INDEX
    Explanations

    references to professional qualifications and experiences

    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
     Dün
    -0.08
    leta
    -0.07
    rika
    -0.07
    "';
    -0.07
    Ïĩη
    -0.06
    ushman
    -0.06
    chner
    -0.06
     Rudd
    -0.06
    ongoose
    -0.06
    ross
    -0.06
    POSITIVE LOGITS
    ıc
    0.07
    ulp
    0.06
    _neighbors
    0.06
    tright
    0.06
    éį
    0.06
    ctl
    0.05
     trav
    0.05
    .optional
    0.05
     Rational
    0.05
    aset
    0.05
    Activations Density 0.008%

    No Known Activations