© 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. 83241
    Prev
    Next
    INDEX
    Explanations

    conditional phrases indicating potential challenges and considerations in various scenarios

    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
    ilo
    -0.06
    auga
    -0.06
    asis
    -0.06
    å¾ħ
    -0.06
    inand
    -0.06
    ektor
    -0.06
    offee
    -0.06
    elman
    -0.06
    串
    -0.05
    nick
    -0.05
    POSITIVE LOGITS
     budget
    0.13
     unavailable
    0.13
     available
    0.12
     availability
    0.11
    available
    0.11
     Budget
    0.11
     budgets
    0.11
    budget
    0.11
    availability
    0.10
    -available
    0.10
    Activations Density 0.062%

    No Known Activations