© 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. 84487
    Prev
    Next
    INDEX
    Explanations

    words associated with ownership and attribution in a document

    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
    anou
    -0.07
    reetings
    -0.07
     Charg
    -0.06
    owie
    -0.06
    cie
    -0.06
    ãĤĩãģĨ
    -0.06
    leads
    -0.06
    ingles
    -0.06
    uegos
    -0.06
    .gs
    -0.06
    POSITIVE LOGITS
    ToDevice
    0.07
    ÅŁi
    0.07
    AttributeValue
    0.06
    ãĥ©ãĤ¤ãĥĪ
    0.06
    ê
    0.06
     Consort
    0.06
    553
    0.06
    Deaths
    0.06
     Hastings
    0.06
     fid
    0.06
    Activations Density 0.000%

    No Known Activations