© 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. 75222
    Prev
    Next
    INDEX
    Explanations

    concepts related to spiritual purification and emotional healing

    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
    azu
    -0.08
    ivar
    -0.08
    eder
    -0.07
     iddi
    -0.07
    anka
    -0.07
    vore
    -0.07
    odom
    -0.07
    manuel
    -0.07
    antz
    -0.07
    ference
    -0.07
    POSITIVE LOGITS
    Atl
    0.07
     Hollow
    0.06
     ne
    0.06
    åįĶ
    0.06
     communications
    0.06
    .scalablytyped
    0.06
     Balance
    0.06
    олиÑĤ
    0.05
     giao
    0.05
     physical
    0.05
    Activations Density 0.001%

    No Known Activations