© 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. 106102
    Prev
    Next
    INDEX
    Explanations

    references to digital object identifiers (DOIs)

    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
    ammo
    -0.08
    ebo
    -0.07
    749
    -0.07
    _EPS
    -0.07
    irth
    -0.06
     æ¬
    -0.06
    éĢģ
    -0.06
    lay
    -0.06
    556
    -0.06
    âĶIJ
    -0.06
    POSITIVE LOGITS
    owitz
    0.07
     slight
    0.07
    usp
    0.06
     Kok
    0.06
     dung
    0.06
    CLU
    0.06
    cce
    0.06
     Sang
    0.06
    imetype
    0.06
    xfff
    0.06
    Activations Density 0.002%

    No Known Activations