© 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. 29987
    Prev
    Next
    INDEX
    Explanations

    specific recommendations followed by their corresponding actions or resolutions

    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
    ild
    -0.09
    uf
    -0.07
    gard
    -0.06
    omo
    -0.06
    aps
    -0.06
    pery
    -0.06
    ê°IJ
    -0.06
    iph
    -0.06
    -depth
    -0.06
     Pompe
    -0.06
    POSITIVE LOGITS
    atory
    0.10
    /request
    0.09
     ìĤ¬íķŃ
    0.09
    ìĤ¬íķŃ
    0.08
    ivec
    0.08
    /tutorial
    0.08
    éĢģæĸĻçĦ¡æĸĻ
    0.07
    ç¿°
    0.07
    iments
    0.07
    ryptography
    0.07
    Activations Density 0.019%

    No Known Activations