© 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. 62147
    Prev
    Next
    INDEX
    Explanations

    elements related to personal stories and relationships

    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
    mrt
    -0.07
    ÑĢоÑĩ
    -0.07
    ÃĹ↵↵
    -0.07
    IGIN
    -0.07
    //{{
    -0.07
    ÑĢÑĮ
    -0.07
    erece
    -0.07
    oris
    -0.07
    266
    -0.07
    podob
    -0.07
    POSITIVE LOGITS
     behind
    0.07
    isc
    0.06
    ami
    0.06
     often
    0.06
    arp
    0.06
     reason
    0.06
     leg
    0.06
    dy
    0.06
    eti
    0.06
     evolution
    0.06
    Activations Density 0.024%

    No Known Activations