© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 106757
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and opportunities for collaboration

    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
     tomorrow
    -0.06
    BuilderInterface
    -0.06
    æŁĦ
    -0.06
    loys
    -0.06
    pras
    -0.06
    ropolitan
    -0.06
    boa
    -0.06
    egend
    -0.06
     sustained
    -0.06
    InstanceOf
    -0.06
    POSITIVE LOGITS
     decided
    0.07
     decision
    0.07
    portun
    0.07
    resi
    0.07
    _macros
    0.07
     mutual
    0.07
     fits
    0.07
    chosen
    0.07
     opportunity
    0.07
     cÃŃ
    0.07
    Activations Density 0.026%

    No Known Activations