© 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. 40656
    Prev
    Next
    INDEX
    Explanations

    phrases expressing intense emotions or awe

    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
    ÑģÑĤÑĢÑĥ
    -0.07
    etat
    -0.06
    oron
    -0.06
     shrink
    -0.06
    ony
    -0.06
    anye
    -0.06
    ÑĢÑĥг
    -0.06
    _altern
    -0.06
     Muj
    -0.06
    antro
    -0.06
    POSITIVE LOGITS
    #ga
    0.07
    />.
    0.07
     Nations
    0.07
    erti
    0.07
    allery
    0.06
    ahi
    0.06
    ahren
    0.06
    907
    0.06
     nations
    0.06
     hart
    0.06
    Activations Density 0.036%

    No Known Activations