© 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. 16491
    Prev
    Next
    INDEX
    Explanations

    terms related to software licensing and modification rights

    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
    iba
    -0.07
    iÄįky
    -0.07
    axon
    -0.07
    kit
    -0.06
    inea
    -0.06
    urum
    -0.06
    sci
    -0.06
    yun
    -0.06
    acker
    -0.06
    çħ§
    -0.06
    POSITIVE LOGITS
    _occ
    0.06
     Pied
    0.06
    ão
    0.06
     lou
    0.05
    assi
    0.05
    رش
    0.05
    orte
    0.05
    rt
    0.05
    agher
    0.05
    ring
    0.05
    Activations Density 0.001%

    No Known Activations