© 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. 93496
    Prev
    Next
    INDEX
    Explanations

    phrases indicating possession or characteristics

    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
    ész
    -0.07
    .epam
    -0.06
    osoph
    -0.06
    .hw
    -0.06
    estate
    -0.06
    еÑĢб
    -0.06
    á»
    -0.06
    IVATE
    -0.06
    etto
    -0.06
    /lic
    -0.06
    POSITIVE LOGITS
    amas
    0.08
     Vital
    0.07
    /cms
    0.06
    ģ
    0.06
    ickle
    0.06
     status
    0.06
    ruz
    0.06
    chas
    0.06
    imenti
    0.06
     Hew
    0.06
    Activations Density 0.024%

    No Known Activations