© 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. 105896
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to loss and destruction

    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
    peater
    -0.07
    nv
    -0.07
    endez
    -0.07
    onet
    -0.06
    als
    -0.06
     Merry
    -0.06
     nets
    -0.05
    osi
    -0.05
    anged
    -0.05
    omo
    -0.05
    POSITIVE LOGITS
     remains
    0.11
     remnants
    0.10
     fragments
    0.10
    æ®ĭ
    0.10
     remaining
    0.09
     fragment
    0.09
    remaining
    0.09
    åī©
    0.09
     remain
    0.08
     Remaining
    0.08
    Activations Density 0.023%

    No Known Activations