© 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. 71405
    Prev
    Next
    INDEX
    Explanations

    expressions related to support and opposition in social or political contexts

    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
    APA
    -0.08
    orc
    -0.07
    irie
    -0.07
    овеÑĢ
    -0.07
    akis
    -0.07
    lecture
    -0.06
    ulk
    -0.06
    anik
    -0.06
    erties
    -0.06
    justify
    -0.06
    POSITIVE LOGITS
     wherever
    0.07
     healthy
    0.07
     entitled
    0.06
     valid
    0.06
    uong
    0.06
     sentiment
    0.06
     whatever
    0.06
    Inflater
    0.05
    èĶµ
    0.05
     whenever
    0.05
    Activations Density 0.026%

    No Known Activations