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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 16362
    Prev
    Next
    INDEX
    Explanations

    terms related to competitive events and rankings

    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
    olie
    -0.06
     Stamp
    -0.06
    iyas
    -0.06
    517
    -0.06
    ãģĵ
    -0.06
     mend
    -0.06
    ximo
    -0.06
    639
    -0.06
    nio
    -0.06
     Batch
    -0.05
    POSITIVE LOGITS
     points
    0.08
     Award
    0.07
    ÏĥÏĨ
    0.07
    ständ
    0.07
    abis
    0.07
    retty
    0.07
    ết
    0.07
     awards
    0.07
     scores
    0.07
     Awards
    0.07
    Activations Density 0.014%

    No Known Activations