© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 78713
    Prev
    Next
    INDEX
    Explanations

    words or phrases indicating a combination of gameplay elements, particularly those related to servers and grilling

    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
    èĪª
    -0.07
    hyth
    -0.07
     Races
    -0.07
     Kaf
    -0.07
    olley
    -0.07
     Bucc
    -0.07
    erif
    -0.07
    MemoryWarning
    -0.07
    _perc
    -0.07
    .SIG
    -0.06
    POSITIVE LOGITS
    heid
    0.07
    stable
    0.06
     ring
    0.06
    éĥ¨å±ĭ
    0.06
     earnings
    0.06
     sum
    0.06
     career
    0.06
    faction
    0.06
     stable
    0.06
     belt
    0.06
    Activations Density 0.000%

    No Known Activations