© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 87638
    Prev
    Next
    INDEX
    Explanations

    references to personal feelings or conditions

    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
    (TEXT
    -0.06
    ¢°
    -0.06
     controvers
    -0.06
    .DateTimePicker
    -0.06
    io
    -0.06
     Cran
    -0.06
    ãģĹãĤĥ
    -0.05
     media
    -0.05
    quest
    -0.05
    (Constant
    -0.05
    POSITIVE LOGITS
     now
    0.08
    iggins
    0.07
    agus
    0.07
    ãĥķãĥĪ
    0.07
    aget
    0.07
    ipeg
    0.07
    yntax
    0.06
    ãĥ¼ãĥ«
    0.06
    .snap
    0.06
     myself
    0.06
    Activations Density 0.000%

    No Known Activations