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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 31-LLAMASCOPE-RES-131K
    6. 44394
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter "z"

    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
    ,
    -0.11
     a
    -0.10
     S
    -0.08
     in
    -0.08
     and
    -0.08
     V
    -0.08
     ex
    -0.08
     to
    -0.08
     (
    -0.08
     
    -0.08
    POSITIVE LOGITS
    ycz
    0.18
    ysz
    0.17
    eci
    0.17
    yp
    0.16
    yst
    0.16
    ek
    0.15
    esz
    0.15
    ynos
    0.15
    ys
    0.15
    yn
    0.15
    Activations Density 0.002%

    No Known Activations