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. 9-LLAMASCOPE-RES-131K
    6. 95740
    Prev
    Next
    INDEX
    Explanations

    names and roles within a publishing context

    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
    ati
    -0.07
     Gazette
    -0.06
     this
    -0.05
     boot
    -0.05
     clear
    -0.05
     Merrill
    -0.05
     air
    -0.05
     so
    -0.05
     it
    -0.05
     if
    -0.05
    POSITIVE LOGITS
    ÑģÑĤÑĢов
    0.09
     ogs
    0.09
    ãĥ³ãĤ¯
    0.08
    _marshall
    0.08
     içi
    0.08
    upa
    0.08
    γκο
    0.08
    .sz
    0.08
    .GetObject
    0.08
    tron
    0.08
    Activations Density 0.019%

    No Known Activations