© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 97939
    Prev
    Next
    INDEX
    Explanations

    phrases that describe the reputation and quality of hotels or restaurants

    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
    ADR
    -0.07
    arendra
    -0.07
    actionDate
    -0.07
    rezent
    -0.07
    rength
    -0.07
    ouro
    -0.06
     поÑĤеÑĢ
    -0.06
    λμ
    -0.06
    лиÑħ
    -0.06
    _Lean
    -0.06
    POSITIVE LOGITS
     popular
    0.07
     neighborhood
    0.07
     exterior
    0.06
     conscient
    0.06
     cons
    0.06
    éľ²
    0.06
    ibilities
    0.06
    ordo
    0.06
     its
    0.06
    avia
    0.06
    Activations Density 0.032%

    No Known Activations