© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 126542
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Earn" and its variations related to obtaining or achieving

    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
    optera
    -0.08
    oppins
    -0.07
    arity
    -0.07
    ponents
    -0.07
    ponent
    -0.07
    eer
    -0.06
    orraine
    -0.06
    aire
    -0.06
    EB
    -0.06
    804
    -0.06
    POSITIVE LOGITS
    ings
    0.11
    ÂŃing
    0.10
    able
    0.08
    ables
    0.08
    INGS
    0.07
    ussen
    0.07
    shaw
    0.07
    hardt
    0.07
    ily
    0.07
    edImage
    0.07
    Activations Density 0.005%

    No Known Activations