© 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. 71371
    Prev
    Next
    INDEX
    Explanations

    references to text formatting and structure

    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
    588
    -0.07
    ÑģÑĮ
    -0.07
    elib
    -0.06
    kart
    -0.06
    iras
    -0.06
    hazi
    -0.06
    ccion
    -0.06
    óz
    -0.06
    /testing
    -0.06
     skew
    -0.06
    POSITIVE LOGITS
    -long
    0.08
    ìĶ©
    0.07
    å·¦åı³
    0.07
    ì§ľ
    0.07
    acter
    0.07
    PerPixel
    0.07
    bor
    0.07
    éĴŁ
    0.07
    -strong
    0.07
    .amazonaws
    0.06
    Activations Density 0.017%

    No Known Activations