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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 5-LLAMASCOPE-RES-131K
    6. 126439
    Prev
    Next
    INDEX
    Explanations

    variations of the verb "become" in different forms and 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
    ificador
    -0.08
    ież
    -0.07
    ÑģÑĤвоÑĢ
    -0.07
    ahkan
    -0.07
    -letter
    -0.07
    ieber
    -0.07
    492
    -0.07
    ãĤ¤ãĥī
    -0.07
    UNUSED
    -0.07
    urgeon
    -0.06
    POSITIVE LOGITS
    ãģķãĤī
    0.06
     Provid
    0.06
     coco
    0.06
     Ziel
    0.05
    代
    0.05
    da
    0.05
     dil
    0.05
    324
    0.05
     æĸ
    0.05
    arih
    0.05
    Activations Density 0.025%

    No Known Activations