© 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. 82929
    Prev
    Next
    INDEX
    Explanations

    instances of the word "River" or its variations in the text

    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
    vla
    -0.09
    upe
    -0.08
    ignum
    -0.08
    å®ħ
    -0.08
    jvu
    -0.07
    antry
    -0.07
    eyle
    -0.07
    ãĥ©ãĤ¯
    -0.07
    rupa
    -0.07
    erais
    -0.07
    POSITIVE LOGITS
    front
    0.08
    ine
    0.07
    dale
    0.07
     compromise
    0.07
    ks
    0.06
     Herman
    0.06
    fy
    0.06
    point
    0.06
    lining
    0.06
     breeze
    0.05
    Activations Density 0.012%

    No Known Activations