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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 22-LLAMASCOPE-RES-131K
    6. 4558
    Prev
    Next
    INDEX
    Explanations

    phrases indicating future actions or expectations

    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
    åĹ
    -0.07
     persever
    -0.07
     coun
    -0.07
    íĮĶ
    -0.07
     Seeder
    -0.07
     accompl
    -0.06
     writ
    -0.06
    stal
    -0.06
    ÙħÙĨ
    -0.06
    è©
    -0.06
    POSITIVE LOGITS
    help
    0.09
     help
    0.08
     helps
    0.08
     helfen
    0.07
    roman
    0.07
    elp
    0.07
    _help
    0.07
    result
    0.07
    rez
    0.07
    gars
    0.07
    Activations Density 0.043%

    No Known Activations