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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 56931
    Prev
    Next
    INDEX
    Explanations

    terms related to coffee and its effects

    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
    #ad
    -0.08
    ิà¹ī
    -0.08
    "":
    -0.07
    ãĢģé«ĺ
    -0.07
    mpz
    -0.07
    ÄĮesk
    -0.07
    ìĽIJìĿ´
    -0.07
    emachine
    -0.07
     disappe
    -0.07
     encount
    -0.07
    POSITIVE LOGITS
    -related
    0.07
    iya
    0.06
    -focused
    0.06
    -induced
    0.06
    ign
    0.06
    /stdc
    0.06
     â̦
    0.06
    .googlecode
    0.06
    abor
    0.06
    -specific
    0.05
    Activations Density 0.040%

    No Known Activations