© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 61375
    Prev
    Next
    INDEX
    Explanations

    specifications related to vehicle performance and power metrics

    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
    itas
    -0.07
     footing
    -0.07
    ãĥ©ãĤ¹
    -0.06
    -toggler
    -0.06
    è°ĵ
    -0.06
    GLOBALS
    -0.06
    -addon
    -0.06
     bÃło
    -0.06
    ë£Į
    -0.06
     tarif
    -0.06
    POSITIVE LOGITS
     torque
    0.09
     Tor
    0.06
     Dane
    0.06
     impress
    0.06
    anness
    0.06
    orque
    0.06
    CRET
    0.06
     force
    0.06
     Force
    0.06
    okes
    0.06
    Activations Density 0.004%

    No Known Activations