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. 96220
    Prev
    Next
    INDEX
    Explanations

    terms related to animal control and responsibility

    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
    deniz
    -0.08
    ï¸
    -0.08
    sky
    -0.08
    ddit
    -0.07
    جا
    -0.07
    ói
    -0.07
    ampo
    -0.06
    mile
    -0.06
    ronic
    -0.06
    .jsp
    -0.06
    POSITIVE LOGITS
    reads
    0.06
     breed
    0.06
    VERTISE
    0.06
     mediation
    0.06
     Breed
    0.06
     mediator
    0.05
     Lust
    0.05
    558
    0.05
    ĥ
    0.05
    PLAN
    0.05
    Activations Density 0.004%

    No Known Activations