Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95852
    Prev
    Next
    INDEX
    Explanations

    time-related terms and market trading 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
    ampa
    -0.07
    .BorderFactory
    -0.06
     Net
    -0.06
    ngör
    -0.06
     net
    -0.06
     and
    -0.06
    leta
    -0.06
     Idol
    -0.06
    icho
    -0.06
    /ca
    -0.05
    POSITIVE LOGITS
    Äįet
    0.07
    linik
    0.07
    ulle
    0.07
    obl
    0.07
    avig
    0.07
    asje
    0.07
    igy
    0.07
    avaÅŁ
    0.07
    ãģ¨ãģĵãĤį
    0.06
    ãĤ·ãĤ¢
    0.06
    Activations Density 0.002%

    No Known Activations