© 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. 16807
    Prev
    Next
    INDEX
    Explanations

    intensifiers or adverbs that emphasize degree or quality

    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
    afen
    -0.07
    bit
    -0.06
    ramid
    -0.06
    ös
    -0.06
     kit
    -0.06
     ce
    -0.06
    ¸
    -0.06
     Pet
    -0.05
    /models
    -0.05
    yer
    -0.05
    POSITIVE LOGITS
    ediator
    0.07
    ieder
    0.07
     ragaz
    0.07
    oud
    0.07
    ียà¸Ķ
    0.06
    ">//
    0.06
    824
    0.06
    /Dk
    0.06
    essaging
    0.06
    ailability
    0.06
    Activations Density 0.050%

    No Known Activations