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. 22-LLAMASCOPE-RES-131K
    6. 4579
    Prev
    Next
    INDEX
    Explanations

    elements related to police investigations and emergency responses

    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
     DefaultValue
    -0.07
    .Predicate
    -0.07
    _MR
    -0.07
    GINE
    -0.07
    åĽ
    -0.07
    ourg
    -0.06
    ichten
    -0.06
     useClass
    -0.06
     Nz
    -0.06
    iverz
    -0.06
    POSITIVE LOGITS
     officers
    0.08
     Officers
    0.07
    ihan
    0.07
    ysz
    0.06
     officer
    0.06
    otton
    0.06
    oled
    0.06
     Specialist
    0.06
    999
    0.06
    amba
    0.06
    Activations Density 0.005%

    No Known Activations