© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 55462
    Prev
    Next
    INDEX
    Explanations

    instances of the word "can" and its variations indicating possibility or ability

    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
    èĥ½
    -0.09
    èĥ½å¤Ł
    -0.09
     BÃĸL
    -0.07
    icens
    -0.07
    »¿
    -0.07
    orge
    -0.07
    indle
    -0.07
    edom
    -0.07
    anca
    -0.06
    amient
    -0.06
    POSITIVE LOGITS
    't
    0.12
    ’t
    0.12
    /w
    0.10
     be
    0.10
    opies
    0.10
    berra
    0.10
    nt
    0.09
    alic
    0.09
     easily
    0.08
     indeed
    0.08
    Activations Density 0.280%

    No Known Activations