© 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. 15-LLAMASCOPE-RES-131K
    6. 2
    Prev
    Next
    INDEX
    Explanations

    listings of performance types and related musical content

    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
    assen
    -0.08
    uger
    -0.07
    ека
    -0.07
     Blasio
    -0.07
    imits
    -0.06
    _CLIP
    -0.06
     earthly
    -0.06
    phanumeric
    -0.06
    apsible
    -0.06
    igh
    -0.06
    POSITIVE LOGITS
     special
    0.08
     Special
    0.07
    special
    0.07
    _special
    0.06
    Special
    0.06
    éĤ¦
    0.06
     Joint
    0.06
     expl
    0.06
    .special
    0.06
     specialty
    0.06
    Activations Density 0.042%

    No Known Activations