© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 119500
    Prev
    Next
    INDEX
    Explanations

    phrases relating to fitting something within constraints or dimensions

    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
    icha
    -0.07
     heav
    -0.06
     heavier
    -0.06
    dump
    -0.06
     heavy
    -0.06
     dumping
    -0.06
     rag
    -0.06
    haven
    -0.06
    reater
    -0.06
    icus
    -0.06
    POSITIVE LOGITS
    obil
    0.07
     HOLDER
    0.07
    aylor
    0.07
    uppy
    0.07
    akra
    0.07
    ÃŃny
    0.07
    _Space
    0.07
     newSize
    0.06
    redit
    0.06
    angent
    0.06
    Activations Density 0.012%

    No Known Activations