© 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. 28793
    Prev
    Next
    INDEX
    Explanations

    phrases that inquire about locations or destinations

    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
    essim
    -0.06
    estr
    -0.06
     sooner
    -0.06
    PRINTF
    -0.06
    ÑĢаÑģÑĤ
    -0.06
    ameda
    -0.06
    osa
    -0.05
     abst
    -0.05
    /light
    -0.05
    acock
    -0.05
    POSITIVE LOGITS
     source
    0.09
    where
    0.09
    (where
    0.08
     where
    0.08
    Where
    0.07
    .SDK
    0.07
    agan
    0.07
    source
    0.07
     location
    0.07
     donde
    0.07
    Activations Density 0.019%

    No Known Activations