© 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. 80893
    Prev
    Next
    INDEX
    Explanations

    mentions of representatives or agents involved in personal or legal relationships

    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
    fon
    -0.07
    éĺħ读次æķ°
    -0.07
    stick
    -0.07
    ÑģÑĤин
    -0.07
    aign
    -0.07
    инкÑĥ
    -0.07
    ãĥ¬ãĤ¤
    -0.07
    akening
    -0.06
    MBProgressHUD
    -0.06
    burgh
    -0.06
    POSITIVE LOGITS
    lessness
    0.06
    iek
    0.06
    _DESCRIPTOR
    0.06
    onn
    0.06
    hip
    0.06
     HIP
    0.06
    HIP
    0.06
    ãģ«ãĤĪ
    0.06
     CDDL
    0.05
     heck
    0.05
    Activations Density 0.024%

    No Known Activations