© 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. 15-LLAMASCOPE-RES-131K
    11. 27146
    Prev
    Next
    INDEX
    Explanations

    specific numerical and coded identifiers related to geographic or geological data

    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
    room
    -0.06
    egg
    -0.06
    oval
    -0.06
    çĽijåIJ¬é¡µéĿ¢
    -0.06
    .IContainer
    -0.05
    ound
    -0.05
    immel
    -0.05
     Ihren
    -0.05
     Tin
    -0.05
    190
    -0.05
    POSITIVE LOGITS
    ë²Ī
    0.09
    âĢ²
    0.09
    ábado
    0.08
    itmap
    0.08
    âĢ³
    0.07
    ovsky
    0.07
    à¤¿à¤Ľ
    0.07
    etxt
    0.07
    SCII
    0.07
    ipline
    0.07
    Activations Density 0.028%

    No Known Activations