© 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. 29472
    Prev
    Next
    INDEX
    Explanations

    instances of the word "presentation" and its variations

    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
    ombo
    -0.08
    oll
    -0.07
    ambi
    -0.07
    uv
    -0.07
    olas
    -0.07
    SA
    -0.06
    itet
    -0.06
    ometr
    -0.06
    s
    -0.06
    eric
    -0.06
    POSITIVE LOGITS
    iment
    0.11
    ational
    0.10
    wahl
    0.09
    tlement
    0.09
     Ñģобой
    0.08
    929
    0.08
    orial
    0.08
    eÄį
    0.08
    -day
    0.08
    iments
    0.08
    Activations Density 0.040%

    No Known Activations