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

    Neuronpedia

    Jacobian LensNEW
    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. 15-LLAMASCOPE-RES-131K
    11. 88614
    Prev
    Next
    INDEX
    Explanations

    phrases indicating personal experiences and reflections on academic or professional journeys

    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
    stalk
    -0.06
    hta
    -0.06
     claims
    -0.06
    jez
    -0.06
    ella
    -0.06
    hod
    -0.06
     orig
    -0.06
     모ëĵł
    -0.06
     claim
    -0.06
    amon
    -0.06
    POSITIVE LOGITS
     pii
    0.08
    豪
    0.07
    ynes
    0.07
    اتÙĩ
    0.07
    achi
    0.06
    spent
    0.06
     Bilim
    0.06
     eldre
    0.06
    Blockly
    0.06
    upa
    0.06
    Activations Density 0.022%

    No Known Activations