© 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. 77504
    Prev
    Next
    INDEX
    Explanations

    references to subscription services and premium content offerings

    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
    -devel
    -0.06
     priv
    -0.06
     Taken
    -0.05
     quote
    -0.05
     Cay
    -0.05
     Enforcement
    -0.05
    immer
    -0.05
    ago
    -0.05
     eos
    -0.05
     blank
    -0.05
    POSITIVE LOGITS
     entire
    0.11
    åħ¨éĥ¨
    0.09
    complete
    0.09
     entirety
    0.09
    å®Įæķ´
    0.08
     AppModule
    0.08
     complete
    0.08
    acia
    0.08
    inand
    0.08
    ndx
    0.08
    Activations Density 0.026%

    No Known Activations