© 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. 40652
    Prev
    Next
    INDEX
    Explanations

    information about discrepancies and comparisons between different data or entities

    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
    ãĥ¼ãĥĬ
    -0.09
    iku
    -0.07
    inta
    -0.06
    vely
    -0.06
    itti
    -0.06
    okies
    -0.06
    .fits
    -0.06
    大åħ¨
    -0.06
     touching
    -0.06
    Occurred
    -0.06
    POSITIVE LOGITS
     actual
    0.11
    actual
    0.10
    å®ŀéĻħ
    0.10
    Actual
    0.09
     reality
    0.08
     actually
    0.08
    (actual
    0.08
     ÑĦакÑĤи
    0.08
    actually
    0.08
     exact
    0.08
    Activations Density 0.008%

    No Known Activations