© 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 EvalsExportsinterp-engineNEWAPI 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. 91995
    Prev
    Next
    INDEX
    Explanations

    specific names and titles associated with people and roles

    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
    ncmp
    -0.07
     kå
    -0.07
    ведиÑĤе
    -0.07
    -alist
    -0.07
     داخ
    -0.07
    .bluetooth
    -0.07
    еÑĤи
    -0.07
    esc
    -0.07
    /lists
    -0.07
    eÄį
    -0.07
    POSITIVE LOGITS
     Credit
    0.07
     episode
    0.07
     credit
    0.06
     segment
    0.06
     bro
    0.06
    Credit
    0.06
     Chapter
    0.06
     Segment
    0.06
     Episode
    0.06
    KeyType
    0.06
    Activations Density 0.000%

    No Known Activations