© 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. 78590
    Prev
    Next
    INDEX
    Explanations

    instances of personal involvement and collective experiences

    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
    eti
    -0.06
    Ī
    -0.06
     empath
    -0.06
     TMPro
    -0.06
     adım
    -0.05
     ration
    -0.05
    forc
    -0.05
     prive
    -0.05
     Laden
    -0.05
    دÙħ
    -0.05
    POSITIVE LOGITS
    .getElementsBy
    0.07
     opc
    0.07
     Thought
    0.07
     got
    0.07
    ÅĽmy
    0.07
    inalg
    0.07
    士
    0.06
    spent
    0.06
     went
    0.06
    _attachments
    0.06
    Activations Density 0.039%

    No Known Activations