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. 11478
    Prev
    Next
    INDEX
    Explanations

    forms and variations of the prefix "ir-" or similar phonetic patterns

    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
     Gallagher
    -0.08
    ASIC
    -0.07
     Clarence
    -0.07
    íıŃ
    -0.07
    ãĥ¥
    -0.07
    tul
    -0.07
    ERGY
    -0.07
    ãĤĥ
    -0.07
    ¦¬
    -0.07
    tures
    -0.07
    POSITIVE LOGITS
    pective
    0.19
    ist
    0.14
    olute
    0.10
    ponsible
    0.10
    ome
    0.09
    pectives
    0.09
    olvable
    0.08
    itable
    0.08
    olutely
    0.07
    isible
    0.07
    Activations Density 0.002%

    No Known Activations