© 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. 27156
    Prev
    Next
    INDEX
    Explanations

    phrases indicating requests for more information or follow-up actions

    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
    ivo
    -0.07
    juan
    -0.06
    gow
    -0.06
    sys
    -0.06
    igos
    -0.06
    erre
    -0.06
    roit
    -0.06
    iano
    -0.06
    éĻ£
    -0.06
    sis
    -0.06
    POSITIVE LOGITS
    rung
    0.06
    ÑĪев
    0.06
     Hybrid
    0.06
    arkin
    0.06
     GObject
    0.06
    peaker
    0.05
    jit
    0.05
    nek
    0.05
    QR
    0.05
    aje
    0.05
    Activations Density 0.014%

    No Known Activations