© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 129587
    Prev
    Next
    INDEX
    Explanations

    elements related to programming structure and documentation

    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
    ignant
    -0.06
    kla
    -0.06
    ours
    -0.06
    inci
    -0.06
    ouch
    -0.06
    gressive
    -0.06
    StringEncoding
    -0.06
    Directories
    -0.06
    udio
    -0.06
    atories
    -0.06
    POSITIVE LOGITS
     here
    0.25
    _here
    0.21
    here
    0.20
     Here
    0.19
     aquÃŃ
    0.19
    Here
    0.19
    _HERE
    0.18
     HERE
    0.18
     aqui
    0.17
     здеÑģÑĮ
    0.17
    Activations Density 0.097%

    No Known Activations