© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 123307
    Prev
    Next
    INDEX
    Explanations

    references to locations and offices

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     elsewhere
    -0.07
    ów
    -0.06
    acter
    -0.06
     patron
    -0.06
     Patrol
    -0.06
     overall
    -0.06
     Else
    -0.06
     Tomorrow
    -0.06
    mor
    -0.05
    otp
    -0.05
    POSITIVE LOGITS
    åĬŀåħ¬
    0.09
    ursors
    0.07
    é§ħå¾ĴæŃ©
    0.07
    .opendaylight
    0.07
    JKLM
    0.07
    Ñħодим
    0.07
    太éĥİ
    0.07
     offices
    0.06
    vál
    0.06
     recru
    0.06
    Activations Density 0.022%

    No Known Activations