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. 4899
    Prev
    Next
    INDEX
    Explanations

    actions related to sports play

    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
    itez
    -0.08
    its
    -0.06
     Koh
    -0.06
    ller
    -0.06
    ites
    -0.06
    pee
    -0.06
    åĿĽ
    -0.06
    dig
    -0.06
    ter
    -0.06
     Brewer
    -0.06
    POSITIVE LOGITS
    OptionsMenu
    0.08
     onBind
    0.07
    stride
    0.07
    ERTICAL
    0.07
    ValuePair
    0.07
     ev
    0.07
    òng
    0.07
    entral
    0.07
     strides
    0.07
    ollision
    0.07
    Activations Density 0.017%

    No Known Activations