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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1149
    Prev
    Next
    INDEX
    Explanations

    punctuation and numeric values related to academic research

    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
    anon
    -0.07
    èo
    -0.07
    ưa
    -0.07
    CLIENT
    -0.07
     Lah
    -0.07
    htag
    -0.06
    clients
    -0.06
     springfox
    -0.06
    ÅĻÃŃd
    -0.06
    LAB
    -0.06
    POSITIVE LOGITS
    ces
    0.07
    668
    0.07
    Falsy
    0.06
    dden
    0.06
    SetColor
    0.06
    247
    0.06
     Wit
    0.06
     chor
    0.06
    alto
    0.06
    epar
    0.06
    Activations Density 0.001%

    No Known Activations