© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 84639
    Prev
    Next
    INDEX
    Explanations

    instances of the article "a" and associated determiners or qualifiers

    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
    cia
    -0.08
    ÑĥÑĢÑģ
    -0.07
    ura
    -0.07
    lsi
    -0.07
    ipment
    -0.07
    ajs
    -0.07
    лади
    -0.07
    alion
    -0.07
    çª
    -0.07
    -gnu
    -0.07
    POSITIVE LOGITS
     which
    0.10
     fact
    0.09
    .k
    0.08
    which
    0.08
     nd
    0.07
     cui
    0.07
     feat
    0.07
     something
    0.07
     testament
    0.06
     indication
    0.06
    Activations Density 0.052%

    No Known Activations