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. 22-LLAMASCOPE-RES-131K
    6. 5496
    Prev
    Next
    INDEX
    Explanations

    terms relating to assumptions and their implications in various 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
     obstruction
    -0.07
    orna
    -0.07
    ëĭ¤ê°Ģ
    -0.06
    iges
    -0.06
    ono
    -0.06
    ush
    -0.06
    864
    -0.06
    ermen
    -0.06
    apat
    -0.06
    -eye
    -0.06
    POSITIVE LOGITS
     about
    0.15
    _about
    0.12
     About
    0.12
    about
    0.12
     ABOUT
    0.11
    made
    0.11
     tentang
    0.11
    -about
    0.11
    åħ³äºİ
    0.11
     made
    0.10
    Activations Density 0.015%

    No Known Activations