© 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. 15-LLAMASCOPE-RES-131K
    11. 61949
    Prev
    Next
    INDEX
    Explanations

    concepts related to karma and its effects on life

    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
    елен
    -0.07
    olit
    -0.07
    icho
    -0.07
     sabah
    -0.07
    å®ľ
    -0.07
    аниÑĨ
    -0.07
     ç«ĭ
    -0.06
    {text
    -0.06
    RIEND
    -0.06
     sacr
    -0.06
    POSITIVE LOGITS
     k
    0.08
     e
    0.07
     lif
    0.06
    ìĬ¤ì½Ķ
    0.06
    uem
    0.06
    adesh
    0.06
     Claus
    0.06
    alian
    0.06
     karma
    0.06
     soul
    0.06
    Activations Density 0.102%

    No Known Activations