Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95955
    Prev
    Next
    INDEX
    Explanations

    car models and their specifications

    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
    pliers
    -0.07
    latlong
    -0.07
    icast
    -0.07
    ActionBar
    -0.06
    á»ī
    -0.06
    #End
    -0.06
    oproject
    -0.06
    EQUAL
    -0.06
     forState
    -0.06
    ạn
    -0.06
    POSITIVE LOGITS
    rack
    0.07
    odos
    0.06
    resi
    0.06
     klu
    0.06
    еви
    0.06
     ath
    0.06
    estr
    0.06
     strong
    0.06
    olas
    0.06
     pretty
    0.06
    Activations Density 0.005%

    No Known Activations