© 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. 16838
    Prev
    Next
    INDEX
    Explanations

    phrases related to readiness and preparation for future events

    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
    :numel
    -0.06
    ký
    -0.06
    .clearRect
    -0.05
    nyder
    -0.05
     unstable
    -0.05
    ãģ¾
    -0.05
    .innerWidth
    -0.05
    rám
    -0.05
    onne
    -0.05
    orthy
    -0.05
    POSITIVE LOGITS
     later
    0.19
    later
    0.15
     Later
    0.15
     später
    0.15
    Later
    0.15
     when
    0.11
    when
    0.11
     pozdÄĽji
    0.10
     pozdÄĽ
    0.10
     ready
    0.10
    Activations Density 0.063%

    No Known Activations