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. 43485
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols in the text

    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
     thru
    -0.06
     (“
    -0.06
    agine
    -0.06
    umas
    -0.06
    ıcı
    -0.06
    ientos
    -0.06
     tonight
    -0.06
    å¹¹ç·ļ
    -0.05
    ulfilled
    -0.05
    à¤¿à¤Ľ
    -0.05
    POSITIVE LOGITS
     clients
    0.09
     client
    0.08
     standout
    0.08
     Clients
    0.08
    Clients
    0.07
    Strength
    0.07
     impress
    0.07
     strength
    0.07
     defence
    0.07
     strengths
    0.07
    Activations Density 0.004%

    No Known Activations