© 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. 71045
    Prev
    Next
    INDEX
    Explanations

    the name "Cam" or similar variations and references related to it

    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
    uous
    -0.07
    quez
    -0.07
    umat
    -0.07
    amt
    -0.07
    ncia
    -0.07
    heard
    -0.07
    weathermap
    -0.07
    itional
    -0.07
    _CSR
    -0.06
    UMAN
    -0.06
    POSITIVE LOGITS
    ouflage
    0.09
    oufl
    0.08
    eras
    0.08
    argo
    0.07
    eroon
    0.07
     Spider
    0.07
     McConnell
    0.07
     Cam
    0.07
    ero
    0.07
    Spider
    0.07
    Activations Density 0.020%

    No Known Activations