© 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. 87290
    Prev
    Next
    INDEX
    Explanations

    the word "necessary" and its variations, indicating discussions on essential conditions or requirements

    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
    ernity
    -0.07
    ston
    -0.07
    scribe
    -0.07
    ridge
    -0.07
     expectancy
    -0.07
    eneric
    -0.07
    ians
    -0.07
    orna
    -0.07
    iggs
    -0.07
    alle
    -0.07
    POSITIVE LOGITS
    mente
    0.11
    lessly
    0.09
     evil
    0.09
     evils
    0.08
    ful
    0.08
    /request
    0.08
    evil
    0.07
    fol
    0.07
     minimum
    0.07
     Malk
    0.07
    Activations Density 0.015%

    No Known Activations