© 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. 77191
    Prev
    Next
    INDEX
    Explanations

    occurrences of names and titles related to reporting or journalism

    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
    ako
    -0.06
    uddle
    -0.06
    ungalow
    -0.06
    ells
    -0.06
     Tribe
    -0.06
    oe
    -0.05
    ills
    -0.05
    abant
    -0.05
    loat
    -0.05
    gener
    -0.05
    POSITIVE LOGITS
    VERTISEMENT
    0.07
    HX
    0.07
     генеÑĢа
    0.07
    ãĤ¤ãĥ³ãĥĪ
    0.07
     ="";↵
    0.07
     بزر
    0.07
     å½±
    0.07
    GetProcAddress
    0.07
    ,...↵↵
    0.07
    ìĥ
    0.07
    Activations Density 0.003%

    No Known Activations