© 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. 129065
    Prev
    Next
    INDEX
    Explanations

    references to despair and psychological struggle

    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
     addCriterion
    -0.07
    è°±
    -0.07
    holders
    -0.06
     normals
    -0.06
    ãĥ³ãĤ¹
    -0.06
     Roo
    -0.06
     Rookie
    -0.06
    zell
    -0.06
    izable
    -0.06
    наÑĢод
    -0.06
    POSITIVE LOGITS
     depths
    0.10
    ëŀĮ
    0.07
    è°·
    0.07
     bottom
    0.07
    405
    0.07
    ias
    0.07
     dug
    0.07
    _bottom
    0.07
    iden
    0.07
    bole
    0.07
    Activations Density 0.026%

    No Known Activations