© 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. 75350
    Prev
    Next
    INDEX
    Explanations

    topics related to communication technologies and their infrastructures

    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
    aptor
    -0.06
    umpt
    -0.06
    sock
    -0.06
     kav
    -0.06
    iros
    -0.06
    ç¾½
    -0.06
     Gentle
    -0.06
    _HAL
    -0.06
    æ½ľ
    -0.06
     observable
    -0.06
    POSITIVE LOGITS
    çĺ
    0.07
    ula
    0.07
    .rmi
    0.06
     ÑĢеÑĩ
    0.06
    ichi
    0.06
     addCriterion
    0.06
     подав
    0.06
     ÑģвÑıзи
    0.06
    uche
    0.06
    ieten
    0.06
    Activations Density 0.069%

    No Known Activations