© 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. 55752
    Prev
    Next
    INDEX
    Explanations

    references to destruction and loss related to literature and history

    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
    anki
    -0.07
    hei
    -0.07
     Overall
    -0.06
    çļĦæĺ¯
    -0.06
    ãĥ§
    -0.06
     Faul
    -0.06
    opp
    -0.06
     Leakage
    -0.06
    abb
    -0.06
    rique
    -0.06
    POSITIVE LOGITS
     except
    0.09
    except
    0.09
    æīĢæľī
    0.08
     remaining
    0.07
     Shea
    0.07
     ÙħÙĪجÙĪد
    0.07
    ãģĻãģ¹ãģ¦
    0.07
    Except
    0.07
    _except
    0.07
     inhabit
    0.07
    Activations Density 0.036%

    No Known Activations