© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 61226
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to signal processing and physical interactions in nuclear models

    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
     favor
    -0.06
     dor
    -0.06
    ols
    -0.06
     rap
    -0.06
    :
    -0.06
     Fre
    -0.06
     der
    -0.06
    uni
    -0.05
     hen
    -0.05
     for
    -0.05
    POSITIVE LOGITS
    ühr
    0.09
    reffen
    0.07
    vů
    0.07
     Annunci
    0.07
     Äijỡ
    0.07
    gesi
    0.07
    ÏĦεÏį
    0.07
    éĺħ读次æķ°
    0.07
    InputBorder
    0.07
    -facing
    0.07
    Activations Density 0.159%

    No Known Activations