Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 31-LLAMASCOPE-RES-131K
    6. 43877
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to bouncing or recovery

    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
    imers
    -0.07
    ret
    -0.07
    asis
    -0.07
    éļIJ
    -0.07
    ansi
    -0.06
    reta
    -0.06
    isis
    -0.06
    issing
    -0.06
    throp
    -0.06
    ippers
    -0.06
    POSITIVE LOGITS
     bounce
    0.12
     bounced
    0.12
    -back
    0.10
    back
    0.10
     bouncing
    0.10
    bounce
    0.10
     back
    0.09
     off
    0.09
     rebound
    0.09
     forward
    0.09
    Activations Density 0.007%

    No Known Activations