© 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. 5-LLAMASCOPE-RES-131K
    11. 126446
    Prev
    Next
    INDEX
    Explanations

    phrases related to the act of running or traversing distances

    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
    lead
    -0.06
    quo
    -0.06
     Lead
    -0.06
     born
    -0.06
    ily
    -0.06
    ophon
    -0.06
    qua
    -0.06
    dam
    -0.06
    607
    -0.05
     lead
    -0.05
    POSITIVE LOGITS
    beck
    0.09
    .scalablytyped
    0.08
    istrovstvÃŃ
    0.07
     Diaz
    0.07
    DCF
    0.07
    odyn
    0.07
    TPL
    0.07
    PÅĻed
    0.07
    ivas
    0.07
    ZD
    0.07
    Activations Density 0.006%

    No Known Activations