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. 5188
    Prev
    Next
    INDEX
    Explanations

    phrases related to competitive racing events, focusing on achieving success and notable performances

    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
    bish
    -0.08
    boro
    -0.07
    ampoline
    -0.06
    ivity
    -0.06
     Roosevelt
    -0.06
    ãĤ¤ãĤº
    -0.06
    .scalablytyped
    -0.06
    notation
    -0.06
    duit
    -0.06
    ÐĬ
    -0.06
    POSITIVE LOGITS
     poles
    0.08
     Maver
    0.07
     pole
    0.07
    pole
    0.06
     defending
    0.06
    orges
    0.06
     Lap
    0.06
     Nico
    0.06
     lap
    0.06
     Gamb
    0.06
    Activations Density 0.008%

    No Known Activations