© 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. 15-LLAMASCOPE-RES-131K
    11. 90377
    Prev
    Next
    INDEX
    Explanations

    numerical data and technical specifications related to systems and methods

    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
    262
    -0.07
    _MODULES
    -0.07
    cao
    -0.06
    illis
    -0.06
    ulkan
    -0.06
    ugin
    -0.06
    _strength
    -0.06
    ambre
    -0.06
    peon
    -0.06
    umu
    -0.06
    POSITIVE LOGITS
     stain
    0.06
    æ¡£
    0.06
     NOTE
    0.06
     chast
    0.06
    ForObject
    0.06
     Ñģв
    0.06
     кÑĥÑģÑĤ
    0.06
     olmam
    0.05
    etin
    0.05
    .Round
    0.05
    Activations Density 0.018%

    No Known Activations