Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95929
    Prev
    Next
    INDEX
    Explanations

    terms related to violence and crime

    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
    perature
    -0.07
    cke
    -0.07
    ะ
    -0.07
    minster
    -0.07
     liv
    -0.06
    оÑĪ
    -0.06
    eyn
    -0.06
     nga
    -0.06
    Elite
    -0.06
    имв
    -0.06
    POSITIVE LOGITS
    ovsky
    0.07
    rage
    0.07
    .Internal
    0.06
    abr
    0.06
    iesel
    0.06
    acz
    0.06
    ag
    0.06
     GTK
    0.05
    du
    0.05
    469
    0.05
    Activations Density 0.000%

    No Known Activations