© 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. 57220
    Prev
    Next
    INDEX
    Explanations

    themes related to cultural identity and historical context

    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
     VÅ¡ech
    -0.10
    gnore
    -0.10
    uniacid
    -0.09
    .scalablytyped
    -0.09
    éĺħ读次æķ°
    -0.09
    اÙĦÙĬا
    -0.09
    dıģında
    -0.09
    yalty
    -0.09
    iParam
    -0.09
    lacak
    -0.08
    POSITIVE LOGITS
    â
    0.10
     â
    0.07
     ``
    0.07
    в
    0.07
     _____
    0.07
    .".
    0.07
     [âĢ¦]
    0.06
     also
    0.06
     âĢ¦
    0.06
     âĵĺ
    0.06
    Activations Density 0.325%

    No Known Activations