© 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. 75172
    Prev
    Next
    INDEX
    Explanations

    titles and roles related to events, organizations, and publications

    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
     Bonds
    -0.07
    ary
    -0.07
    ard
    -0.07
    éĩı
    -0.07
    rov
    -0.07
    /inet
    -0.07
    eno
    -0.07
    /oct
    -0.06
    nid
    -0.06
    åħIJ
    -0.06
    POSITIVE LOGITS
    (s
    0.09
    :
    0.08
    çļĦæĺ¯
    0.07
    llib
    0.06
    ÑĮÑı
    0.06
    chure
    0.06
    ा:
    0.06
    illisecond
    0.06
    eturn
    0.06
    :&
    0.06
    Activations Density 0.023%

    No Known Activations