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. 43862
    Prev
    Next
    INDEX
    Explanations

    terms related to low-budget themes or productions

    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
    ÙĬÙĨÙĩ
    -0.07
     Ulus
    -0.07
    innamon
    -0.07
    ioxide
    -0.06
     Picker
    -0.06
    -addon
    -0.06
    oria
    -0.06
    иÑģÑĤÑĢа
    -0.06
     opak
    -0.06
    umont
    -0.06
    POSITIVE LOGITS
    key
    0.14
     key
    0.13
     rent
    0.12
     brow
    0.11
    b
    0.11
    budget
    0.11
    -key
    0.11
     budget
    0.10
    down
    0.10
    life
    0.10
    Activations Density 0.009%

    No Known Activations