© 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. 40744
    Prev
    Next
    INDEX
    Explanations

    instances of unusual or attention-grabbing events

    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
    IDGET
    -0.07
    _meas
    -0.06
     Fist
    -0.06
     Wid
    -0.06
    ighth
    -0.06
    åIJ§
    -0.06
     Suche
    -0.06
    Yeah
    -0.06
    .dataTables
    -0.06
     Unt
    -0.06
    POSITIVE LOGITS
    rada
    0.07
     panic
    0.07
    469
    0.07
     then
    0.06
    Łèĥ½
    0.06
    ẹn
    0.06
     Herz
    0.06
    eum
    0.06
    cum
    0.06
    ppelin
    0.06
    Activations Density 0.035%

    No Known Activations