© 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. 61134
    Prev
    Next
    INDEX
    Explanations

    phrases related to effort and investment in time or resources

    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
    467
    -0.07
    apis
    -0.07
    errick
    -0.07
    290
    -0.07
    olle
    -0.07
    addock
    -0.07
    ceipt
    -0.06
    odash
    -0.06
    ouched
    -0.06
    646
    -0.06
    POSITIVE LOGITS
     effort
    0.08
     into
    0.08
     Into
    0.08
    .scalablytyped
    0.07
    alink
    0.07
    into
    0.07
    zte
    0.07
     INTO
    0.06
    ÂŃi
    0.06
    YPES
    0.06
    Activations Density 0.025%

    No Known Activations