© 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. 40667
    Prev
    Next
    INDEX
    Explanations

    specific types of contact information

    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
    ombre
    -0.08
    ç§Ģ
    -0.08
    æ¬
    -0.07
    plen
    -0.07
    Reserved
    -0.07
    viz
    -0.07
    ogui
    -0.07
    ogra
    -0.07
    afort
    -0.07
    klä
    -0.07
    POSITIVE LOGITS
     contact
    0.08
     telephone
    0.08
     daytime
    0.07
     cell
    0.07
     Koch
    0.07
     phone
    0.07
    telephone
    0.06
    çĶµè¯Ŀ
    0.06
     cellphone
    0.06
     Fax
    0.06
    Activations Density 0.011%

    No Known Activations