© 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. 118455
    Prev
    Next
    INDEX
    Explanations

    concepts related to existence and quantity

    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
    ologne
    -0.06
     kijken
    -0.06
     dahi
    -0.06
    Ñīин
    -0.06
    ENTE
    -0.06
     nues
    -0.06
    ationToken
    -0.06
    ente
    -0.06
     Shuffle
    -0.06
    νι
    -0.06
    POSITIVE LOGITS
     handful
    0.13
     dozens
    0.13
     many
    0.12
     hundreds
    0.12
     few
    0.11
     several
    0.10
     thousands
    0.10
     Hundreds
    0.10
     number
    0.10
     countless
    0.10
    Activations Density 0.039%

    No Known Activations