© 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. 15-LLAMASCOPE-RES-131K
    11. 27321
    Prev
    Next
    INDEX
    Explanations

    comparative phrases indicating value, effectiveness, and risks

    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
    antine
    -0.09
    izen
    -0.08
    meni
    -0.08
    berger
    -0.08
    izik
    -0.08
    ï¼Ĭ
    -0.08
    redo
    -0.07
    adele
    -0.07
    еÑĢин
    -0.07
    ÌĨ
    -0.07
    POSITIVE LOGITS
     than
    0.07
     because
    0.06
     unless
    0.06
     whereas
    0.05
     Bent
    0.05
    81
    0.05
    _than
    0.05
     Jelly
    0.05
    -than
    0.05
     Bloc
    0.05
    Activations Density 0.027%

    No Known Activations