© 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 EvalsExportsAPI 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. 76634
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "news" and its variations

    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
    berger
    -0.06
    ovel
    -0.06
    leck
    -0.06
    -
    -0.05
    unden
    -0.05
    aders
    -0.05
    aba
    -0.05
    se
    -0.05
     laure
    -0.05
    vs
    -0.05
    POSITIVE LOGITS
    linkplain
    0.08
    igua
    0.08
     ^{°}
    0.08
    ÐIJÑĢÑħÑĸв
    0.07
    kees
    0.07
    ços
    0.07
    aliz
    0.07
    AdapterManager
    0.07
    quential
    0.07
    ENAME
    0.07
    Activations Density 0.000%

    No Known Activations