© 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. 90244
    Prev
    Next
    INDEX
    Explanations

    adverbs that describe intensity or manner of actions

    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
     resp
    -0.08
    emic
    -0.07
    ellular
    -0.07
     amis
    -0.07
    iesel
    -0.07
    onda
    -0.07
    alars
    -0.06
     vra
    -0.06
    .jet
    -0.06
    inator
    -0.06
    POSITIVE LOGITS
    mente
    0.08
    (er
    0.08
    engu
    0.07
    ħn
    0.07
     Ring
    0.07
     mẽ
    0.07
    à¹Ĩ
    0.06
    zeitig
    0.06
     enough
    0.06
    wards
    0.06
    Activations Density 0.066%

    No Known Activations