© 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. 78244
    Prev
    Next
    INDEX
    Explanations

    information related to publication details and copyright

    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
     lifestyle
    -0.07
    -0.06
     soon
    -0.06
     ob
    -0.06
     lifestyles
    -0.06
     top
    -0.06
     alt
    -0.06
    .
    -0.06
    Âł
    -0.06
     pop
    -0.06
    POSITIVE LOGITS
    agu
    0.10
    .TypeString
    0.09
     YYS
    0.08
    StackNavigator
    0.08
    /Peak
    0.08
    /WebAPI
    0.08
    @nate
    0.08
    å¹´çļĦ
    0.08
    PTY
    0.08
    atcher
    0.08
    Activations Density 0.004%

    No Known Activations