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. 5048
    Prev
    Next
    INDEX
    Explanations

    elements related to collaboration and interaction in various contexts

    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
    ç»ĻæĪij
    -0.07
    ix
    -0.06
    ens
    -0.06
    ãĢĤ她
    -0.06
    oret
    -0.06
    让æĪij
    -0.06
     which
    -0.06
    igli
    -0.06
     коÑĤоÑĢÑĥÑİ
    -0.06
     because
    -0.05
    POSITIVE LOGITS
     there
    0.15
     Ù쨥ÙĨ
    0.14
     we
    0.13
     it
    0.12
     they
    0.12
    there
    0.11
     Äijây
    0.11
     оно
    0.10
     you
    0.10
     this
    0.10
    Activations Density 0.095%

    No Known Activations