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. 22-LLAMASCOPE-RES-131K
    6. 5509
    Prev
    Next
    INDEX
    Explanations

    terms related to financial regulatory actions and misconduct

    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
    _tF
    -0.09
    _mE
    -0.09
    _mC
    -0.09
    _mB
    -0.09
    _tE
    -0.08
    å»ł
    -0.08
    /GPL
    -0.08
     licensors
    -0.08
    cdecl
    -0.08
    _IW
    -0.08
    POSITIVE LOGITS
     customer
    0.09
     customers
    0.08
     bonuses
    0.07
     bonus
    0.07
     overd
    0.07
     branch
    0.07
     
    0.07
     opening
    0.06
     Branch
    0.06
     cultures
    0.06
    Activations Density 0.007%

    No Known Activations