© 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. 5-LLAMASCOPE-RES-131K
    11. 126505
    Prev
    Next
    INDEX
    Explanations

    instances where apostrophes are used in possessive or contraction forms

    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
    dash
    -0.06
    ajs
    -0.06
    lep
    -0.06
    licken
    -0.06
    جÙħ
    -0.06
    egin
    -0.06
    iez
    -0.06
    leur
    -0.06
    oint
    -0.06
    ÏĢÏĮ
    -0.06
    POSITIVE LOGITS
    atre
    0.07
    ê·
    0.06
    átel
    0.06
    anced
    0.06
    chie
    0.06
    寸
    0.06
    izyon
    0.06
    laÄį
    0.06
     vitam
    0.06
    iona
    0.06
    Activations Density 0.005%

    No Known Activations