© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 126949
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate simplicity or ease of use

    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
    mers
    -0.08
    aversable
    -0.07
    PropertyChanged
    -0.07
    ively
    -0.07
    mic
    -0.07
    pile
    -0.07
    κÎŃ
    -0.07
    chestra
    -0.07
    mits
    -0.07
    chers
    -0.07
    POSITIVE LOGITS
     dÃłng
    0.11
    -to
    0.10
    going
    0.09
    /simple
    0.09
    ies
    0.07
    /fast
    0.07
    (er
    0.07
    -as
    0.07
    D
    0.06
    ening
    0.06
    Activations Density 0.028%

    No Known Activations