Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 56030
    Prev
    Next
    INDEX
    Explanations

    mentions of student loan assistance programs

    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
    .tbl
    -0.08
    untime
    -0.08
     Inch
    -0.07
    neys
    -0.07
    iams
    -0.07
    .Adapter
    -0.07
    ساÙĨÛĮ
    -0.07
    .ham
    -0.07
     à¸Ħาส
    -0.07
    ãģĦãĤĦ
    -0.07
    POSITIVE LOGITS
     unintention
    0.06
    iva
    0.06
    atto
    0.06
    â
    0.06
    amation
    0.06
     zip
    0.05
     Heller
    0.05
     Irr
    0.05
    elia
    0.05
     wee
    0.05
    Activations Density 0.008%

    No Known Activations