© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 16796
    Prev
    Next
    INDEX
    Explanations

    terms related to rental policies and pet-friendly accommodations

    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
    eyse
    -0.08
    orgen
    -0.08
     Allocator
    -0.07
    jvu
    -0.07
    _iface
    -0.07
    óż
    -0.07
    .datatables
    -0.07
    }}],↵
    -0.07
     *)((
    -0.07
    _ros
    -0.07
    POSITIVE LOGITS
     pets
    0.09
     dogs
    0.09
     Policy
    0.08
     pet
    0.07
     policy
    0.07
    Policy
    0.06
     breeds
    0.06
     ver
    0.06
     weight
    0.06
     Dogs
    0.06
    Activations Density 0.004%

    No Known Activations