© 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. 82793
    Prev
    Next
    INDEX
    Explanations

    key structural components of sentences, particularly words that indicate significant meaning or function within 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
     equ
    -0.07
    230
    -0.06
     SPDX
    -0.06
    BILE
    -0.06
     prag
    -0.06
    REFERRED
    -0.06
     barg
    -0.06
    ÙĬØ©
    -0.06
    frau
    -0.06
    phyl
    -0.06
    POSITIVE LOGITS
     Cove
    0.08
    Segue
    0.07
    inish
    0.07
    ::-
    0.07
    ofire
    0.07
     Sır
    0.07
    amas
    0.07
     defaultMessage
    0.06
    AMY
    0.06
    myp
    0.06
    Activations Density 0.000%

    No Known Activations