© 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. 9-LLAMASCOPE-RES-131K
    11. 95644
    Prev
    Next
    INDEX
    Explanations

    phrases indicating safety hazards and improper practices

    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
    .scalablytyped
    -0.08
    linger
    -0.07
    omitempty
    -0.07
    Ðĭ
    -0.07
    мага
    -0.06
     Angiosper
    -0.06
    antro
    -0.06
     wireType
    -0.06
    GenerationStrategy
    -0.06
    CallCheck
    -0.06
    POSITIVE LOGITS
    ISCO
    0.07
    ghan
    0.06
    lav
    0.06
    ropdown
    0.06
    forman
    0.05
    ẩu
    0.05
    Ĥ¨
    0.05
    åĿĬ
    0.05
    sel
    0.05
    orado
    0.05
    Activations Density 0.029%

    No Known Activations