© 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. 17-LLAMASCOPE-RES-131K
    6. 106923
    Prev
    Next
    INDEX
    Explanations

    references to numbers related to count or sequence

    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
    ppers
    -0.08
    altar
    -0.08
    .way
    -0.08
    essler
    -0.07
    å¥ī
    -0.07
    å¹³æĪIJ
    -0.07
    è¼ī
    -0.07
    uples
    -0.07
    ulumi
    -0.07
    iddle
    -0.07
    POSITIVE LOGITS
    pon
    0.05
    ophobia
    0.05
     dec
    0.05
    IFA
    0.05
     split
    0.05
    izable
    0.05
    ↵
    0.05
     cst
    0.05
    ih
    0.05
    245
    0.05
    Activations Density 0.000%

    No Known Activations