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. 44124
    Prev
    Next
    INDEX
    Explanations

    occurrences of the verb "to speak" in various forms and contexts

    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
    alo
    -0.07
    oris
    -0.07
    оÑĢÑĭ
    -0.07
    ory
    -0.07
    ories
    -0.07
    ious
    -0.06
    adian
    -0.06
    ife
    -0.06
    oth
    -0.06
    ilo
    -0.06
    POSITIVE LOGITS
    elden
    0.12
    elt
    0.11
    eld
    0.09
    ende
    0.08
    elper
    0.08
    elter
    0.08
    kte
    0.08
    eldorf
    0.08
     playable
    0.08
    kt
    0.08
    Activations Density 0.002%

    No Known Activations