© 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. 5-LLAMASCOPE-RES-131K
    6. 126447
    Prev
    Next
    INDEX
    Explanations

    the word "out" in various contexts

    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
    uzzle
    -0.07
    Ľ°
    -0.07
    iston
    -0.07
    geois
    -0.06
    leftJoin
    -0.06
    ked
    -0.06
    ffects
    -0.06
     lesser
    -0.06
    obile
    -0.06
     root
    -0.06
    POSITIVE LOGITS
    reff
    0.07
    -www
    0.07
    LTR
    0.07
    lat
    0.07
    ttp
    0.07
    yer
    0.07
    we
    0.07
     kla
    0.06
    rippling
    0.06
    andas
    0.06
    Activations Density 0.004%

    No Known Activations