© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 56270
    Prev
    Next
    INDEX
    Explanations

    phrases or clauses that specify conditions or clarifications

    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
     whose
    -0.06
    whose
    -0.06
     baÅŁÄ±na
    -0.06
    aign
    -0.06
    sson
    -0.06
    appings
    -0.06
    aryawan
    -0.05
     so
    -0.05
     inse
    -0.05
     Tail
    -0.05
    POSITIVE LOGITS
     equ
    0.07
     compared
    0.07
    lamaz
    0.07
     compares
    0.07
    ague
    0.07
    odore
    0.07
    loon
    0.07
    vider
    0.07
    ores
    0.07
    vecs
    0.06
    Activations Density 0.012%

    No Known Activations