© 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. 15-LLAMASCOPE-RES-131K
    6. 90120
    Prev
    Next
    INDEX
    Explanations

    phrases indicating connections and relationships between various pieces of information or data

    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
    ivre
    -0.08
    é
    -0.07
    andal
    -0.06
    ueur
    -0.06
    urus
    -0.06
     à¤Ĩध
    -0.06
    .truth
    -0.06
    allas
    -0.06
    Sab
    -0.06
     ruk
    -0.06
    POSITIVE LOGITS
     Mayer
    0.07
     ded
    0.06
     pData
    0.06
     strengthened
    0.06
    ember
    0.06
    acades
    0.06
    671
    0.06
    ردÙĩ
    0.06
     infer
    0.06
    aines
    0.06
    Activations Density 0.001%

    No Known Activations