© 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. 103829
    Prev
    Next
    INDEX
    Explanations

    possessives and personal pronouns in the text

    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
    keley
    -0.07
    iona
    -0.07
    conti
    -0.06
    znik
    -0.06
     Agenda
    -0.06
    aby
    -0.06
    idable
    -0.06
    irie
    -0.06
    (gcf
    -0.06
     communion
    -0.06
    POSITIVE LOGITS
    ÏĦιÏĥ
    0.07
    obia
    0.07
    è±
    0.06
    anean
    0.06
    kul
    0.06
    warts
    0.06
     Af
    0.06
     Assigned
    0.06
     internals
    0.06
     terr
    0.06
    Activations Density 0.001%

    No Known Activations