© 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. 5-LLAMASCOPE-RES-131K
    11. 125943
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and ellipses that signify pauses or interruptions in text

    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
    _EXTERN
    -0.07
    dl
    -0.07
    usercontent
    -0.07
    vro
    -0.07
    ãģ©ãģĨ
    -0.07
    λά
    -0.07
    berger
    -0.06
    owell
    -0.06
    interop
    -0.06
    cisi
    -0.06
    POSITIVE LOGITS
    ium
    0.07
    uck
    0.07
    ολ
    0.06
    jar
    0.06
     away
    0.06
    pta
    0.06
    atri
    0.06
     jig
    0.06
     cuc
    0.06
    igrations
    0.06
    Activations Density 0.004%

    No Known Activations