© 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. 5-LLAMASCOPE-RES-131K
    11. 126415
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of "name" and its use in different contexts

    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
    oron
    -0.07
    سÙĦ
    -0.07
    asel
    -0.07
    ãģ°ãģĭãĤĬ
    -0.07
    å°Ħ
    -0.06
    ayette
    -0.06
    ruit
    -0.06
     пÑĢок
    -0.06
    ocoa
    -0.06
    743
    -0.06
    POSITIVE LOGITS
    br
    0.07
    plate
    0.07
    íģ¼
    0.07
    less
    0.07
    akan
    0.06
     Simmons
    0.06
     Folk
    0.06
    hung
    0.06
     folk
    0.06
    £
    0.06
    Activations Density 0.002%

    No Known Activations