© 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. 15-LLAMASCOPE-RES-131K
    11. 27217
    Prev
    Next
    INDEX
    Explanations

    prepositions and phrases indicating location or association

    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
    uta
    -0.07
     Sesso
    -0.07
    oble
    -0.06
    áÄį
    -0.06
    osta
    -0.06
    ozilla
    -0.06
     Honest
    -0.06
    otts
    -0.06
     petite
    -0.06
    à¹Ģà¸
    -0.06
    POSITIVE LOGITS
    bard
    0.06
    eward
    0.06
    "<?
    0.06
    attr
    0.06
    .DAL
    0.06
    pherd
    0.06
     skup
    0.06
    mpar
    0.06
    ElementType
    0.06
    straints
    0.05
    Activations Density 0.005%

    No Known Activations