© 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. 57319
    Prev
    Next
    INDEX
    Explanations

    instances of the word "another" and variations related to repetition or addition

    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
     m
    -0.07
    aku
    -0.06
    773
    -0.06
    msp
    -0.05
     i
    -0.05
    673
    -0.05
    atz
    -0.05
    /downloads
    -0.05
    ua
    -0.05
     Handy
    -0.05
    POSITIVE LOGITS
     iteration
    0.08
    ovnÄĽ
    0.08
    iteration
    0.08
    asty
    0.08
    rada
    0.08
    ding
    0.08
    otto
    0.08
    äºľ
    0.07
    -ÑĤаки
    0.07
    /false
    0.07
    Activations Density 0.016%

    No Known Activations