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

    Neuronpedia

    Jacobian LensNEW
    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. 106635
    Prev
    Next
    INDEX
    Explanations

    reference to time intervals and contextual relationships

    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
    :animated
    -0.06
    erne
    -0.06
    isan
    -0.06
    ido
    -0.06
    enstein
    -0.06
    ura
    -0.06
    oba
    -0.06
     ÎŁÎ¹ÎºÎ¿
    -0.06
    idia
    -0.06
    ToLocal
    -0.06
    POSITIVE LOGITS
     such
    0.24
    such
    0.20
    ä¾ĭå¦Ĥ
    0.16
     SUCH
    0.16
     including
    0.15
     ÑĤакими
    0.14
    eg
    0.14
     ÑĤакиÑħ
    0.14
     like
    0.14
     eg
    0.13
    Activations Density 0.136%

    No Known Activations