© 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. 106092
    Prev
    Next
    INDEX
    Explanations

    phrases related to expectations and anticipated outcomes

    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
    rell
    -0.07
    zeit
    -0.06
    coni
    -0.06
    amik
    -0.06
    ios
    -0.06
    ensor
    -0.06
    ument
    -0.06
    ellow
    -0.06
     Columbia
    -0.06
    ContentPane
    -0.06
    POSITIVE LOGITS
     considering
    0.08
    given
    0.07
     given
    0.07
    405
    0.07
    _trace
    0.06
    ivec
    0.06
    ắc
    0.06
    ÑĢаÑģ
    0.06
    associated
    0.06
    _UNS
    0.06
    Activations Density 0.006%

    No Known Activations