© 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. 58831
    Prev
    Next
    INDEX
    Explanations

    references to trademarks and communication devices

    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
    upe
    -0.07
    nict
    -0.07
    ct
    -0.07
    ÛĮÙĦ
    -0.07
    _TAC
    -0.07
    ç´ł
    -0.06
    Sibling
    -0.06
    _stdio
    -0.06
    åĨ³
    -0.06
    Äįit
    -0.06
    POSITIVE LOGITS
     method
    0.08
     methods
    0.08
     METHOD
    0.08
    icip
    0.06
    .method
    0.06
     teachings
    0.06
     claims
    0.06
     invention
    0.06
    ÏģÏĮÏĤ
    0.06
     claim
    0.06
    Activations Density 0.039%

    No Known Activations