© 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. 125881
    Prev
    Next
    INDEX
    Explanations

    prepositions and related phrases indicating relationships or connections

    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
    зÑĮ
    -0.06
    ÃŃsto
    -0.06
    iden
    -0.06
    Äįást
    -0.06
    uzzi
    -0.06
    elerik
    -0.06
    anda
    -0.06
    ling
    -0.06
    cliffe
    -0.06
     wur
    -0.06
    POSITIVE LOGITS
     xhttp
    0.06
    .Inner
    0.06
     (::
    0.06
    æī¬
    0.06
    -body
    0.06
    ìĹŃ
    0.06
    severity
    0.06
    _$_
    0.06
    PRECATED
    0.06
    aceae
    0.06
    Activations Density 0.004%

    No Known Activations