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. 11440
    Prev
    Next
    INDEX
    Explanations

    elements related to location and community spaces

    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
    roduced
    -0.07
    yleft
    -0.07
    APTER
    -0.07
    обÑīе
    -0.07
    llx
    -0.06
     erotik
    -0.06
    @nate
    -0.06
    levator
    -0.06
    .Std
    -0.06
    ì¡
    -0.06
    POSITIVE LOGITS
     full
    0.19
     filled
    0.16
     overflowing
    0.14
     loaded
    0.14
     packed
    0.14
     laden
    0.13
     br
    0.13
     litter
    0.13
    full
    0.13
     FULL
    0.13
    Activations Density 0.267%

    No Known Activations