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. 43445
    Prev
    Next
    INDEX
    Explanations

    references to doors and openings

    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
    apl
    -0.07
    akit
    -0.06
    urgeon
    -0.06
    MBOL
    -0.06
    rosso
    -0.06
     Tato
    -0.06
    Async
    -0.06
     plagiar
    -0.05
    VIDIA
    -0.05
    ëĮĢíĸī
    -0.05
    POSITIVE LOGITS
     locked
    0.16
     locks
    0.16
     unlocked
    0.16
     lock
    0.16
     locking
    0.15
     unlock
    0.14
     unlocking
    0.14
     latch
    0.14
     LOCK
    0.14
    -lock
    0.13
    Activations Density 0.053%

    No Known Activations