© 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. 74789
    Prev
    Next
    INDEX
    Explanations

    specific instances of geographical or publication dates related to literary works

    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
    cade
    -0.06
     pinch
    -0.06
    otle
    -0.06
     Vladim
    -0.06
    iece
    -0.06
     Becker
    -0.06
    ihan
    -0.06
    eck
    -0.06
     Laz
    -0.06
    area
    -0.06
    POSITIVE LOGITS
    ino
    0.07
    ponible
    0.07
    inos
    0.07
    idget
    0.06
    374
    0.06
    Ú
    0.06
    .frames
    0.06
    ediator
    0.06
    STALL
    0.06
    HRESULT
    0.06
    Activations Density 0.010%

    No Known Activations