© 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. 57174
    Prev
    Next
    INDEX
    Explanations

    phrases indicating economic struggles and social challenges

    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
    lsi
    -0.07
    orque
    -0.07
    rollo
    -0.07
    errupted
    -0.07
    izona
    -0.07
    roti
    -0.07
    ittings
    -0.06
     åIJī
    -0.06
    .tex
    -0.06
    acha
    -0.06
    POSITIVE LOGITS
    ume
    0.08
     increasingly
    0.07
     lag
    0.07
    UME
    0.07
     often
    0.07
    ÙĦاÙĨ
    0.06
     Buck
    0.06
    aran
    0.06
    ="../../../
    0.06
    sm
    0.06
    Activations Density 0.038%

    No Known Activations