© 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. 9-LLAMASCOPE-RES-131K
    11. 96982
    Prev
    Next
    INDEX
    Explanations

    indicators of starting points or origins in a narrative

    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
     Há»ĵng
    -0.08
    locker
    -0.07
    rrha
    -0.07
    ahu
    -0.06
    izr
    -0.06
    imet
    -0.06
    eday
    -0.06
    ioni
    -0.06
    unei
    -0.06
    outil
    -0.06
    POSITIVE LOGITS
    ULL
    0.06
    ulumi
    0.06
    raf
    0.06
    irim
    0.06
    atype
    0.06
     rencont
    0.06
    اسÙĬ
    0.06
     Rot
    0.06
    ãĥ³ãĥģ
    0.06
    ablish
    0.06
    Activations Density 0.000%

    No Known Activations