© 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. 77017
    Prev
    Next
    INDEX
    Explanations

    references to titanium in various contexts

    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
    alam
    -0.07
    aleb
    -0.07
     Ding
    -0.06
     Aviv
    -0.06
    prak
    -0.06
    asy
    -0.06
    GenericType
    -0.06
    ared
    -0.06
     Wing
    -0.06
    ale
    -0.06
    POSITIVE LOGITS
     dioxide
    0.07
    @nate
    0.07
    ede
    0.06
    axon
    0.06
    orta
    0.06
    593
    0.06
    toi
    0.06
    ίδ
    0.06
    Äħ
    0.06
    595
    0.06
    Activations Density 0.004%

    No Known Activations