© 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. 16779
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate prerequisites or actions that must occur before something else can take place

    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
    Sector
    -0.07
    opsis
    -0.07
    zik
    -0.07
    æĤŁ
    -0.07
    andin
    -0.07
    _sector
    -0.07
    iously
    -0.06
    véd
    -0.06
    theid
    -0.06
    raya
    -0.06
    POSITIVE LOGITS
    å°
    0.07
    ilder
    0.07
     istediÄŁiniz
    0.07
     rushes
    0.07
     tedy
    0.06
    ULLET
    0.06
    èĩ
    0.06
     Sul
    0.06
    εια
    0.06
    636
    0.06
    Activations Density 0.008%

    No Known Activations