Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5059
    Prev
    Next
    INDEX
    Explanations

    sports statistics and team information

    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
    yles
    -0.07
     champ
    -0.06
    наÑĤ
    -0.06
     Aber
    -0.06
    dados
    -0.06
     chambers
    -0.06
     Warn
    -0.06
    .SDK
    -0.06
     people
    -0.06
    ardy
    -0.06
    POSITIVE LOGITS
    peare
    0.07
    hait
    0.07
     Pey
    0.07
    ktor
    0.06
     CON
    0.06
    .ErrorMessage
    0.06
     roster
    0.06
    ï¼Ĵï¼IJ
    0.06
     Development
    0.06
     FIFA
    0.06
    Activations Density 0.007%

    No Known Activations