© 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. 87112
    Prev
    Next
    INDEX
    Explanations

    attributes related to image dimensions and website structural elements

    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
    onu
    -0.08
    avenport
    -0.07
    _sentences
    -0.07
    iddi
    -0.07
    μβ
    -0.07
    riott
    -0.07
    ór
    -0.07
    uitka
    -0.07
    lug
    -0.07
    ilha
    -0.07
    POSITIVE LOGITS
     force
    0.06
     hide
    0.06
     transfer
    0.06
     please
    0.05
     ifndef
    0.05
    ãĥ«ãĥĪ
    0.05
    tics
    0.05
    uch
    0.05
    please
    0.05
     Kaiser
    0.05
    Activations Density 0.013%

    No Known Activations