© 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. 93878
    Prev
    Next
    INDEX
    Explanations

    future intentions or plans expressed in the form of "will" statements

    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
    оли
    -0.07
    vido
    -0.07
    ÙĨØ´
    -0.07
    аÑĢÑĩ
    -0.07
    illes
    -0.06
    ÑĢеб
    -0.06
    olicit
    -0.06
    olic
    -0.06
    ots
    -0.06
    iken
    -0.06
    POSITIVE LOGITS
     CascadeType
    0.07
    transparent
    0.06
    horn
    0.06
    ĸī
    0.06
    asca
    0.06
    -make
    0.06
    andro
    0.06
    amped
    0.06
    osing
    0.06
    amping
    0.06
    Activations Density 0.026%

    No Known Activations