© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 87101
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "will" and its context related to future events or actions

    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
    å¾ĭ
    -0.06
     Morm
    -0.06
    sei
    -0.06
    isphere
    -0.06
    udeau
    -0.06
     oslo
    -0.06
    å§Ķåijĺ
    -0.06
    lotte
    -0.06
     barg
    -0.06
    dad
    -0.05
    POSITIVE LOGITS
     host
    0.09
     hosting
    0.08
    host
    0.08
     hosts
    0.08
    hosts
    0.08
    omik
    0.07
     offer
    0.07
    laz
    0.07
    Host
    0.07
    vault
    0.07
    Activations Density 0.019%

    No Known Activations