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. 4896
    Prev
    Next
    INDEX
    Explanations

    punctuation marks associated with statements or quotes

    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
    eyse
    -0.08
    ãi
    -0.08
    ephir
    -0.08
    AGO
    -0.08
    atsapp
    -0.07
    eba
    -0.07
    stå
    -0.07
     však
    -0.07
     denen
    -0.07
    avras
    -0.07
    POSITIVE LOGITS
     there
    0.11
     after
    0.11
     since
    0.10
     although
    0.10
     in
    0.10
     during
    0.10
     while
    0.10
     if
    0.10
     when
    0.10
     for
    0.09
    Activations Density 0.079%

    No Known Activations