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. 9-LLAMASCOPE-RES-131K
    6. 95996
    Prev
    Next
    INDEX
    Explanations

    terms related to sound frequency and light wavelengths

    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
    abyrin
    -0.06
    ebi
    -0.06
     local
    -0.06
    ouden
    -0.06
     here
    -0.06
    chts
    -0.06
     I
    -0.05
     re
    -0.05
     this
    -0.05
     Greenwood
    -0.05
    POSITIVE LOGITS
    .scalablytyped
    0.08
    .range
    0.08
    lacak
    0.08
    ãĥªãĤ«
    0.08
     subrange
    0.07
    Pocket
    0.07
    ARA
    0.07
    .Layout
    0.07
    AMED
    0.07
    æ±ł
    0.07
    Activations Density 0.053%

    No Known Activations