© 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. 78830
    Prev
    Next
    INDEX
    Explanations

    sections or markers indicating a break or transition in content

    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
    eda
    -0.07
    ong
    -0.07
    olem
    -0.07
    ing
    -0.07
    Ø©
    -0.07
    ern
    -0.06
    KA
    -0.06
    esco
    -0.06
    esome
    -0.06
    essian
    -0.06
    POSITIVE LOGITS
    CharacterSet
    0.07
    neau
    0.07
    ainment
    0.07
    ©
    0.07
    seys
    0.07
    clud
    0.07
    iage
    0.07
    ÄĽstÃŃ
    0.07
    ghi
    0.07
    sey
    0.07
    Activations Density 0.003%

    No Known Activations