© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 125735
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate classification or categorization

    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
    еж
    -0.07
    orgh
    -0.06
    ç«ĭãģ¦
    -0.06
    izontally
    -0.06
    agon
    -0.06
    letal
    -0.06
    arl
    -0.06
    contri
    -0.06
     engel
    -0.06
    /pm
    -0.06
    POSITIVE LOGITS
    oday
    0.07
    ÂĿ
    0.07
    elix
    0.07
    enance
    0.06
    pone
    0.06
    _DISP
    0.06
    itta
    0.06
    athom
    0.06
     partida
    0.06
    ÑĨиÑĤ
    0.06
    Activations Density 0.006%

    No Known Activations