© 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. 118498
    Prev
    Next
    INDEX
    Explanations

    sequences that appear to be web addresses or URLs

    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
    lient
    -0.07
    rike
    -0.06
     Hawth
    -0.06
    emade
    -0.06
    iser
    -0.05
    pecies
    -0.05
    farm
    -0.05
    eos
    -0.05
    icho
    -0.05
    ily
    -0.05
    POSITIVE LOGITS
     fitte
    0.08
     Cyr
    0.07
    OVE
    0.07
    ÑĢозÑĥм
    0.07
    usercontent
    0.07
    á»ijn
    0.07
    ENCIL
    0.07
    ÑĥÑĢн
    0.07
    à¸Ķำ
    0.07
    zzo
    0.07
    Activations Density 0.027%

    No Known Activations