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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5187
    Prev
    Next
    INDEX
    Explanations

    elements related to online business and service offerings

    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
    ÙĢ
    -0.07
    legg
    -0.06
    openh
    -0.06
    ibble
    -0.06
    ë°ĺ
    -0.06
    nio
    -0.06
    estic
    -0.06
     "_
    -0.06
    .lista
    -0.06
    ÑĪибка
    -0.06
    POSITIVE LOGITS
    .com
    0.16
    .blogspot
    0.15
    @gmail
    0.14
    .org
    0.12
    .wordpress
    0.11
    @yahoo
    0.11
    adays
    0.10
    .net
    0.10
    .COM
    0.10
    @hotmail
    0.09
    Activations Density 0.136%

    No Known Activations