© 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. 76892
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and dates

    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
    asar
    -0.06
     Oct
    -0.06
    ings
    -0.06
     pylab
    -0.06
    å¥
    -0.06
    ubat
    -0.06
    赫
    -0.06
    обÑĢаж
    -0.06
     overt
    -0.06
     iddi
    -0.06
    POSITIVE LOGITS
    otime
    0.09
    itaire
    0.07
    owitz
    0.07
    _attempts
    0.07
    unas
    0.07
    engo
    0.07
    avage
    0.06
    presso
    0.06
    umn
    0.06
    bean
    0.06
    Activations Density 0.008%

    No Known Activations