© 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. 29723
    Prev
    Next
    INDEX
    Explanations

    references to email components such as subject lines and body text

    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
     è¾
    -0.06
    ifo
    -0.06
    hoe
    -0.06
    RS
    -0.06
     domic
    -0.06
    .qq
    -0.06
    iov
    -0.06
    urls
    -0.06
    versations
    -0.06
    lete
    -0.06
    POSITIVE LOGITS
     title
    0.07
    title
    0.07
    umber
    0.07
    æłĩé¢ĺ
    0.07
    tit
    0.07
     tit
    0.07
    :title
    0.07
    .expr
    0.07
     header
    0.07
     Subject
    0.06
    Activations Density 0.003%

    No Known Activations