© 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. 9-LLAMASCOPE-RES-131K
    11. 95584
    Prev
    Next
    INDEX
    Explanations

    references to collections or groups of items, particularly in an academic or analytical context

    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
     physical
    -0.06
     Physical
    -0.06
    bove
    -0.06
    hoo
    -0.06
    aling
    -0.06
     Well
    -0.06
    ers
    -0.05
     enc
    -0.05
    _physical
    -0.05
    ivos
    -0.05
    POSITIVE LOGITS
     Baghd
    0.08
    oftware
    0.08
    reau
    0.08
    unca
    0.07
    íļį
    0.07
    ãģ¹ãģį
    0.07
    VISION
    0.07
    frauen
    0.07
    illion
    0.07
    ButtonText
    0.07
    Activations Density 0.002%

    No Known Activations