© 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. 26888
    Prev
    Next
    INDEX
    Explanations

    references to luxury and high-quality experiences or items

    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
     mobile
    -0.07
    978
    -0.07
     and
    -0.07
    into
    -0.06
    .
    -0.06
    478
    -0.06
     static
    -0.06
     head
    -0.06
    RO
    -0.06
     count
    -0.06
    POSITIVE LOGITS
    usercontent
    0.10
    apan
    0.08
    istrovstvÃŃ
    0.08
    UpInside
    0.08
    ÑĪин
    0.08
    afil
    0.07
    ì§Ŀ
    0.07
    Ïģαβ
    0.07
    .fhir
    0.07
    quire
    0.07
    Activations Density 0.030%

    No Known Activations