© 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. 126213
    Prev
    Next
    INDEX
    Explanations

    terms related to data collection and usage practices

    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
    473
    -0.07
     Accounts
    -0.06
    ritt
    -0.06
     accounts
    -0.06
    _batch
    -0.06
     Bans
    -0.06
     ФоÑĢ
    -0.06
     Mechanical
    -0.06
     Original
    -0.05
    .batch
    -0.05
    POSITIVE LOGITS
    å¾ģ
    0.06
    elu
    0.06
    obre
    0.06
    oby
    0.06
    omat
    0.06
    ke
    0.06
    mong
    0.06
    .AddParameter
    0.06
    ierz
    0.06
    esel
    0.06
    Activations Density 0.001%

    No Known Activations