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. 43539
    Prev
    Next
    INDEX
    Explanations

    connections to popular music and media references

    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
    quip
    -0.07
    ostel
    -0.06
    adera
    -0.06
    dap
    -0.06
    iene
    -0.06
    Pointer
    -0.06
    alars
    -0.06
    기ëĬĶ
    -0.06
    862
    -0.06
    enger
    -0.06
    POSITIVE LOGITS
     Lands
    0.09
     Gold
    0.07
    lands
    0.07
    Gold
    0.07
    ilver
    0.06
     Dreams
    0.06
    rome
    0.06
     lands
    0.06
    Isn
    0.06
     Sara
    0.06
    Activations Density 0.004%

    No Known Activations