© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 59831
    Prev
    Next
    INDEX
    Explanations

    references to locations or contexts within the text

    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
    place
    -0.06
    ping
    -0.06
    our
    -0.06
    track
    -0.06
    'ın
    -0.06
     dzie
    -0.05
    Ñĵ
    -0.05
    while
    -0.05
    085
    -0.05
    ensa
    -0.05
    POSITIVE LOGITS
     Lesser
    0.08
    (æ°´
    0.07
    emplates
    0.07
    -addons
    0.07
     Mall
    0.07
    à¹ĩà¸ĩ
    0.07
    vern
    0.07
    aversable
    0.07
    astle
    0.07
    aint
    0.07
    Activations Density 0.038%

    No Known Activations