© 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. 55705
    Prev
    Next
    INDEX
    Explanations

    references to studies, reports, and analyses

    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
    istrovstvÃŃ
    -0.07
    kin
    -0.07
    okin
    -0.06
    ÅĪ
    -0.06
    oud
    -0.06
    dek
    -0.06
    ç¥Ŀ
    -0.06
    stoff
    -0.06
     elek
    -0.06
    åħĪçĶŁ
    -0.06
    POSITIVE LOGITS
     involving
    0.08
     by
    0.07
    Truthy
    0.07
    recent
    0.07
     Dre
    0.06
    omba
    0.06
     released
    0.06
     Transparency
    0.06
    ManagedObject
    0.06
     conducted
    0.06
    Activations Density 0.012%

    No Known Activations