© 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. 3775
    Prev
    Next
    INDEX
    Explanations

    references to transportation and accessibility

    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
    инкÑĥ
    -0.07
     taÅŁÄ±n
    -0.06
    astr
    -0.06
    æĪ¸
    -0.06
     til
    -0.06
    duit
    -0.06
    fst
    -0.06
    omba
    -0.06
    _FIFO
    -0.06
    lien
    -0.06
    POSITIVE LOGITS
     parking
    0.11
     Parking
    0.10
    Parking
    0.10
     directions
    0.09
    assen
    0.08
     Directions
    0.08
     Google
    0.08
    Directions
    0.07
     google
    0.07
    é§ħå¾ĴæŃ©
    0.07
    Activations Density 0.021%

    No Known Activations