© 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. 16204
    Prev
    Next
    INDEX
    Explanations

    numeric values associated with dates or numbers in a sequential format

    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
    ancell
    -0.06
    ennie
    -0.06
    cope
    -0.06
     cath
    -0.06
    rech
    -0.06
     Dynasty
    -0.06
    aná
    -0.06
    LabelText
    -0.06
     NÄĽm
    -0.06
    gré
    -0.06
    POSITIVE LOGITS
    ï¿
    0.07
    ivor
    0.07
    pora
    0.06
    ARAM
    0.06
    combe
    0.06
    "nil
    0.06
    AGED
    0.06
    ãĥ¼ãĥ
    0.06
     Geh
    0.06
    ãĥ¼ãĥį
    0.06
    Activations Density 0.025%

    No Known Activations