© 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. 57223
    Prev
    Next
    INDEX
    Explanations

    phrases related to time or temporal references

    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
    uckle
    -0.08
    mates
    -0.08
    AndPassword
    -0.07
    ÄĽtÅ¡
    -0.07
    HEMA
    -0.07
    clist
    -0.07
    owler
    -0.07
    ijd
    -0.07
     OMIT
    -0.07
    kaar
    -0.07
    POSITIVE LOGITS
    -ci
    0.08
    ;
    0.07
    幸
    0.06
     round
    0.06
     Doyle
    0.05
    iane
    0.05
    891
    0.05
    451
    0.05
     requested
    0.05
     Trophy
    0.05
    Activations Density 0.009%

    No Known Activations