© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 74886
    Prev
    Next
    INDEX
    Explanations

    references to various sectors of economic production and outputs

    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
    agus
    -0.08
    ìľ¨
    -0.08
    asco
    -0.08
    ynom
    -0.07
    μÏĮ
    -0.07
    artz
    -0.07
    igu
    -0.07
     münchen
    -0.07
    abilia
    -0.07
    .setter
    -0.07
    POSITIVE LOGITS
     strip
    0.06
     vari
    0.06
     Rank
    0.06
     annually
    0.06
     rank
    0.06
    recover
    0.06
    adil
    0.06
     processing
    0.06
     exports
    0.06
     industrial
    0.05
    Activations Density 0.009%

    No Known Activations