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. 43540
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 'e'

    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
     ins
    -0.06
     section
    -0.06
     sections
    -0.06
     res
    -0.06
    edn
    -0.06
    ossier
    -0.06
    +N
    -0.06
    /Area
    -0.06
     quote
    -0.06
    estring
    -0.06
    POSITIVE LOGITS
    -mails
    0.14
    -messages
    0.11
    jections
    0.10
    vid
    0.09
    phem
    0.09
    verts
    0.08
    valu
    0.08
    vidence
    0.08
    jected
    0.08
    ruptions
    0.08
    Activations Density 0.006%

    No Known Activations