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. 43851
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Pa" and related variations, suggesting a focus on names or identifiers

    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
    ÃľR
    -0.07
    eus
    -0.07
    eve
    -0.07
    ereum
    -0.06
     Lust
    -0.06
    <dim
    -0.06
    fare
    -0.06
     Scar
    -0.06
    SharedPtr
    -0.06
    fd
    -0.06
    POSITIVE LOGITS
    stry
    0.13
    ola
    0.13
    ired
    0.13
    ule
    0.12
    olini
    0.12
    uly
    0.12
    avo
    0.11
    uper
    0.11
    ÅĦst
    0.10
    olina
    0.10
    Activations Density 0.006%

    No Known Activations