© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 16073
    Prev
    Next
    INDEX
    Explanations

    details about charter services and related activities

    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
     inline
    -0.07
     marathon
    -0.06
     Walk
    -0.06
     lodging
    -0.06
    ountain
    -0.06
     downhill
    -0.06
    ardo
    -0.06
     snow
    -0.06
     inland
    -0.06
     hotel
    -0.06
    POSITIVE LOGITS
     Seznam
    0.07
    çĪ½
    0.07
    INCLUDED
    0.07
    ĩ´
    0.07
     vessels
    0.07
    blas
    0.07
     vessel
    0.07
    capt
    0.07
    ificates
    0.07
    èī
    0.07
    Activations Density 0.010%

    No Known Activations