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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5411
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases that highlight noteworthy incidents or events

    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
    opak
    -0.09
    ICLE
    -0.09
    hetto
    -0.09
    ekim
    -0.08
    afone
    -0.08
     erotik
    -0.08
    .xmlbeans
    -0.08
     lidi
    -0.08
    ofilm
    -0.08
     Thiên
    -0.08
    POSITIVE LOGITS
     comics
    0.07
     X
    0.06
     Variant
    0.06
     cost
    0.06
     Comics
    0.06
     /
    0.06
    nh
    0.06
     ID
    0.06
     comic
    0.06
    isl
    0.05
    Activations Density 0.007%

    No Known Activations