© 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. 17-LLAMASCOPE-RES-131K
    11. 79401
    Prev
    Next
    INDEX
    Explanations

    phrases that include the word "like" in various contexts

    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
    isma
    -0.07
    Ả
    -0.07
    lio
    -0.07
    ãģ°ãģĭãĤĬ
    -0.06
    abel
    -0.06
    erable
    -0.06
    hora
    -0.06
    é¤Ĭ
    -0.06
    PE
    -0.06
     bang
    -0.06
    POSITIVE LOGITS
    ani
    0.09
    ANI
    0.08
    å±
    0.07
    ãĥ«ãĥĪ
    0.06
    oba
    0.06
     NDEBUG
    0.06
    osu
    0.06
    ÑĩинÑĭ
    0.06
    felt
    0.06
    "';
    0.06
    Activations Density 0.012%

    No Known Activations